In this episode recorded at CDFAM Barcelona 2026, Johannes Mueller-Roemer presents SubSimX, a pipeline that addresses this by treating subdivision surfaces as a native simulation medium rather than a preprocessing step. Designers work on a standard Catmull-Clark control mesh. Meshing and boundary condition setup happen once. From that point, geometry edits propagate to the existing analysis mesh in seconds, structural feedback is continuous, and the design session never has to stop for remeshing.

The technical core is a precomputed mapping between the control mesh and the volumetric interior, combined with a local mesh-repair step that maintains element quality through large deformations without changing mesh topology. Coupled with RISTRA, Fraunhofer’s GPU-accelerated FEM solver, the system delivers real-time or near real-time structural feedback. Johannes demonstrates how this enables dense design sweeps, topology optimization followed by subdivision refinement, and AI-in-the-loop exploration within practical industrial workflows.

Johannes Mueller-Roemer is Deputy Head of Interactive Engineering Technologies at the Fraunhofer Institute for Computer Graphics Research IGD. He received his PhD from TU Darmstadt in 2019, where his dissertation introduced GPU data structures for tightly coupled modeling and simulation — the foundation SubSimX is built on.

Recorded at CDFAM Barcelona 2026 — https://cdfam.com/barcelona-2026/

In this episode recorded at CDFAM Barcelona 2026, Raul C. Llamas-Sandin presents a GPU-accelerated solver that addresses this directly, reducing solve times for large-scale problems to minutes on a workstation. He covers the key technical features that make it relevant for the built environment: asymmetric tension-compression stress constraints, thermoelastic analysis, and geometric constraint enforcement for fixed architectural elements and fenestration.

Applications demonstrated include bridge design and high-rise structural cores at spans up to 80 meters, as well as free-form architectural geometries exported as watertight STL files ready for digital fabrication. The solver’s modular configuration approach decouples problem definition from the numerical backend, making it adaptable across project types without reengineering the workflow.

Raul is a Future Projects Engineer at Airbus Operations SL and Assistant Professor of Aerospace Engineering at Universidad Europea de Madrid, with over two decades of experience in advanced aircraft design. He holds an MSc in Aerospace Vehicle Design from Cranfield University and 14 patents spanning aerodynamic devices and plasma actuation.

Recorded at CDFAM Barcelona 2026 — https://cdfam.com/barcelona-2026/

In this episode recorded at CDFAM Barcelona 2026, Richard introduces Functional AI as a framework for 3D design automation and walks through Augmenta’s work applying it to real building projects. The technical scope covers agentic AI for MEP path finding, generative modeling of complex structural and mechanical layouts, and progress toward a foundation model for building data. He also discusses what makes non-residential construction — commercial, medical, institutional, and mission critical — a particularly hard problem for AI systems to crack.

The conversation closes on a concrete milestone: two elementary schools in Michigan where the electrical system was fully modeled and delivered using AI-powered generative design, a first for the industry.

Hao (Richard) Zhang is VP of AI and R&D at Augmenta and a Professor in the School of Computing Science at Simon Fraser University. He is a Fellow of the IEEE, a member of the ACM SIGGRAPH Academy, and served as Technical Papers Chair for SIGGRAPH 2025.

Recorded at CDFAM Barcelona 2026 — https://cdfam.com/barcelona-2026/

Mike brings an unusual combination of deep physics intuition - PhD from Columbia studying geometry and electron behavior at the molecular scale - and operational experience from McKinsey and C-suite roles at Swiss aerospace and defense company RUAG. That background informs Arena’s approach to reimagining electromagnetic simulation across semiconductors, aerospace, and automotive sectors.

The conversation covers how Arena is building what they call Artificial Intuition for EM design, the limitations of current simulation approaches, and why a foundation model purpose-built for electromagnetism represents a fundamentally different path forward.

Watch the full presentation:

Full archive at cdfam.com/barcelona-2026/

Pablo Hermoso Moreno, Senior Solutions Architect at NVIDIA, joins CDFAM Barcelona 2026 to discuss how AI is reshaping Computer-Aided Engineering workflows.

Pablo draws on his background in aerospace engineering, aerodynamics at Mercedes F1, and cloud-scale AI at AWS to frame where CAE bottlenecks actually live - and what NVIDIA is doing about them. The conversation covers AI physics and surrogate models for real-time simulation feedback, the role of digital twins, and how agentic AI built on the NVIDIA NeMo stack is automating end-to-end engineering workflows.

He also walks through the AI-Q Blueprint, a production-ready enterprise research agent, and explains how the NeMo Agent Toolkit manages LLM call prioritization to reduce latency without additional hardware investment.

Full presentation and archive at cdfam.com/barcelona-2026/

The next CDFAM Computational Design Symposium takes place July 15-16, 2026 in Washington DC, and submissions are invited from industry, software developers, and academia.

Submit to Present

The event continues the CDFAM Computational Design Symposium format: in-person, technically focused, and structured around practical application of computational design, simulation, AI, and machine learning across engineering, architecture, and manufacturing.

The DC edition extends the program to include additional presentations and roundtable discussions aligned with U.S. government initiatives, with intended engagement between industry, academia, and public-sector stakeholders.

Why Present

CD/DC draws a technically advanced audience from industrial design, engineering, architecture software development, government, and research.

Presenters are expected to go beyond product positioning and engage with substance and evidence: methods, results, open problems, and lessons from deployment.

The format is designed for knowledge transfer and networking, not sales pitches.

Washington DC adds a specific dimension. The audience includes government agencies and national labs with active interest in how computational design, simulation, and AI-driven workflows are being deployed at scale.

These are people who understand the constraints you are working within, have likely encountered the same problems, and in many cases are positioned to collaborate, validate, or extend the work. That makes the conversation after the talk as valuable as the talk itself.

Washington DC adds a further dimension. The audience includes government agencies and national labs with active interest in how computational design, simulation, and AI-driven workflows are being deployed at scale. Presenting here is a direct line to stakeholders who influence procurement, funding, and policy at the program level.

If your work is technically rigorous, deployment-tested, or advancing the state of the field, participating at CDFAM in Washington DC may be the best opportunity to share and connect with others in your space.

Confirmed speakers are already in place from:

NASA Goddard Space Flight Center, Atomic Machines, Boston Dynamics, General Atomics Aeronautical Systems, DARPA, Istari Digital, nTop, Luminary, Arena Physica, Neural Concept, Intact Solutions, Compute Maritime, Cognitive Design, Lexset, C-Infinity, Vinci, 4D.ai, and SysGit.

Space is limited. The program is filling quickly.

Proposal submissions and early bird registration is now available at cdfam.com.

Submit to Present

CD/DC is part of the CDFAM Computational Design Symposium series. Upcoming events: Washington DC, July 2026 / Tokyo, October 2026.

There is a version of computational design that stops at geometry. It produces forms that look organic, patterns that feel complex, outputs that are visually coherent. But the logic underneath is shallow style applied through software rather than behaviour derived from constraints.

Yuan Mu’s work at Nike Innovation is something different.

Her practice sits at the intersection of fabrication, material behavior, and design intent, not as separate concerns to be resolved in sequence, but as a single integrated system. Her background moves through animation, architecture, and textile engineering, and the through-line across all three is the same: understanding how things are made, and rebuilding that logic computationally.

In our interview ahead of her keynote at CDFAM Barcelona, Yuan talks about what it actually takes to close the gap between simulation and physical behavior, why the shift from analog to digital textile production is fundamentally about decoding craft rather than replacing it, and how end-to-end computational workflows change not just the process but the mentality of the people doing the work.

On the relationship between optimization and aesthetics:

“Most of the time, I’m careful not to rely on computational language as an automatic style. Instead, I embed additional layers of parameters into the system — not just geometric variables.

These parameters allow the form to evolve from constraints rather than from a preset visual language. When tuned intentionally, optimization doesn’t just improve performance; it refines the aesthetic.

The visual coherence emerges as a byproduct of logic — but it isn’t applied. It’s negotiated through the system.”

On the learning curve in additive and hybrid manufacturing:

“The learning curve in this field isn’t just about tools — it’s about understanding.

There’s a big difference between knowing and merely knowing of.

Today, software and workflows are more accessible than ever, but accessibility doesn’t automatically mean comprehension.”

On what end-to-end integration actually changes:

“That proximity to making changes your mentality. You become more invested, more curious, and more responsible.

The hands-on problem-solving mindset smooths the workflow. It does require lots of time and depth of knowledge, but I believe that shift toward integrated, end-to-end thinking is what will continue to transform the industry.”

These are not abstract observations. They reflect a specific, hard-won position on what computational design is actually for and what it demands from the people practicing it in a meaningful way.

Yuan will be presenting at CDFAM Barcelona on April 8-9, 2026.

Her keynote is a performance-oriented exploration of textile and apparel design: function-first and speculative, where computation is materially responsive rather than just visually applied.

Read the full interview here: Textile, Rewritten – Yuan Mu, Nike Innovation

Register to Attend

Register to attend CDFAM Barcelona to connect with Yuan pushing the adoption of computational design, AI and machine learning in engineering and architecture.

One role everyone is talking about

The most-viewed listing (by far) this month is a remote position posted via Handshake for a Rhino 3D Specialist to train AI models.

Not to use Rhino. Not to design with Grasshopper. To teach an AI how to do it. You know, replace yourself…

It is not a senior role. It does not require ‘industry experience.’ But it does require deep fluency in Rhino 3D workflows, the kind of software-specific knowledge that has historically been acquired over years of practice on real projects.

More Roles from CDFAM Presenters

BeyondMath, presenting at CDFAM Barcelona next month, have five roles in London across AI research, ML engineering, simulation, software, and a technical account director position, a sign the company is moving from deeper into commercial deployment.

Emmi AI, also presenting in Barcelona, is hiring simulation engineers with domain expertise in crash testing and injection moulding specifically reinforcing that training models need engineers who understand the physics, not just the AI.

Pasteur Labs posted a cluster of roles including Simulation Intelligence Scientist and Applied ML and Simulation Engineering, all fully remote.

Istari Digital is hiring a Digital Engineering Manager and Solutions Software Engineer in the DMV area, both focused on connected engineering infrastructure.

Compute Maritime, presenting NeuralShipper at Barcelona, added three roles including a Machine Learning Engineer and Graduate Naval Architect, both remote from London.

On the aerospace side, General Atomics Aeronautical Systems posted five roles across AI, additive manufacturing, and airframe design. Blue Origin added a Turbomachinery CFD Analyst and Additive Applications Engineer. SpaceX posted roles in aerodynamics, additive manufacturing software, and a Government Affairs Manager in Washington, DC. (side note: the next US CDFAM will be held in DC in July)

Atomic Machines is hiring for an AI CAD Engineer, a job title that would have sounded like science fiction five years ago, and is now one of the least controversial listings on the job board.

Se more at cdfam.com/careers.

If you are interested in working in this field in any way you should definitely Join us in Barcelon, April 8-9, 2026.

Each interview is worth reading on its own. Together, they give a glimpse of what April 8 and 9 is going to look like.

Nico Haag — PhysicsX

From Surrogates to Large Physics Models: Making AI-Native Engineering Work in Production

PhysicsX has roots in Formula One, the engineering problems they have taken on since, across aerospace, automotive, energy, and semiconductors, are not trivial, and the platform they’ve built to address them is worth understanding.

The interview with Nico covers the transition from traditional surrogate modeling to reusable physics intelligence, what the data pipeline for training aerodynamic models actually looks like, and how Large Physics Models are deployed in production rather than staged in a research environment.

His position on the human-in-the-loop question is direct: physics AI expands what engineers can do; it does not remove them from the process.

Read the interview

Hao (Richard) Zhang — Augmenta

Functional AI for 3D Design Automation: From Path Finding to Generative Modeling for Building Construction

Augmenta is working toward something that sounds straightforward until you look at what it actually requires: fully engineered, construction-ready 3D buildings generated from high-level inputs, with MEP systems that are geometrically valid, code-compliant, and buildable from day one.

Richard’s interview introduces a useful distinction between spatial AI and functional AI. The former asks whether a design fits. The latter asks whether it works.

That difference in framing has significant downstream consequences for training objectives, data strategy, and what constitutes a valid output.

Read the interview

Raul C. Llamas-Sandin — Universidad Europea de Madrid & Airbus Operations SL

Unlocking Large-Scale Structural Synthesis: High-Performance GPU Topology Optimization

Raul’s research addresses stress-constrained topology optimization at scales that are actually relevant to structural engineering: models running to hundreds of millions of elements on a single consumer-grade GPU.

The method avoids structural sensitivities, which improves both speed and robustness, while an outer control loop maintains constraint fulfillment throughout.

The interview covers multi-load configurations, mixed materials, self-weight, and tension-compression asymmetry.

He also speaks to the role of AI in accelerating code development and offers perspective from his parallel work in conceptual aircraft design at Airbus. It’s a grounded, technically specific conversation.

Read the interview

Join us in Barcelona

These three interviews represent a fraction of the program.

CDFAM Barcelona brings together practitioners and researchers across computational design, simulation, AI, and advanced manufacturing for two days of technical presentations industry gossip and tapas.

If you’ve been meaning to register, now is the time.

Register to attend — CDFAM Barcelona, April 8–9, 2026

This is a small-group, hands-on session limited to 20 participants, led by Max Gaedtke, leading thermal simulation engineer and developer from nTop.

Over three hours, participants will work through heat exchanger modeling workflows, simulation-ready design techniques, and best practices directly in the software.

ELISAVA School of Design and Engineering, located on La Rambla in central Barcelona, is one of Europe’s leading schools of design and engineering and a fitting venue for a session like this.

Workshop details

• Instructor: Max Gaedtke, nTop

• Date: April 7, 2026, 15:00–18:00

• Location: ELISAVA, La Rambla 30–32, 08002 Barcelona, Room 209

• Capacity: 20 participants

If you’re already attending CDFAM Barcelona and work with thermal management, advanced manufacturing, or computational design workflows, this is a practical way to make use of the day before the symposium.

Space is limited. Register here.

Register for Workshop

Discounted CDFAM Barcelona tickets Thanks to nTop

A limited number of discounted tickets to CDFAM Barcelona (April 8–9) are available courtesy of nTop. Use code nTop50 at checkout for 50% off registration.

If you’re planning to attend the workshop, the symposium runs the following two days at the same location. Don’t wait on either; both have hard capacity limits.

Register for CDFAM Barcelona at 50% off

Last Day for Discounted Registration

Today is the final day to register for CDFAM Barcelona at the discounted rate of €800.

After today, the price moves to €1,000. The symposium runs April 8-9, 2026, at the Barcelona Biomedical Research Park (PRBB), a research facility located directly on the Mediterranean waterfront.

The program is complete. Two full days of technical presentations and case studies spanning computational design, AI-driven engineering, advanced manufacturing, and architectural systems.

Register to Attend

Program Overview

The speaker roster covers a serious cross-section of where computational design and engineering AI are being applied in practice. A partial list:

The April 8th keynote will be delivered by Nike’s Yuan Mu on computational fabrication and algorithmically designed textiles with performance driven toolpathing for Flyknit and 3D printing.

NVIDIA’s Pablo Hermoso Moreno will present on AI surrogate models and agentic CAE workflows, drawing on his background in Formula 1 aerodynamics and cloud-scale AI deployment.

Nico Haag of PhysicsX will discuss the move from narrow surrogates toward large physics models, with external aerodynamics as the concrete case.

Quercus Hernandez of Emmi AI will present on large engineering models for injection moulding and an open-source framework for deploying engineering AI at industrial scale.

Max Gaedtke and Markus Lempke of nTop and Siemens Energy present a closed-loop parametric optimization workflow for turbine blade internal cooling, combining nTop’s implicit geometry engine with a GPU-native conjugate heat transfer solver that cuts time-to-solution by roughly 200x versus conventional finite-volume methods.

Pratap Ranade of Arena AI presents on building a foundation model for electromagnetism to accelerate hardware development across semiconductor, aerospace, and automotive applications, one of the harder unsolved problems in domain-specific engineering AI.

Michael Rosam of Quix presents on consolidating engineering test data and automating R&D analysis workflows, targeting the time lost to fragmented data and manual reporting across hardware development cycles.

Andrew Sartorelli and Tilman Steininger of Synera present across two sessions: the first examining practical AI agent applications in engineering workflows, from requirements extraction to automated simulation setup and reporting; the second delivered jointly with Juan De Dios Escribano Felguera of SEAT-CUPRA, demonstrating how computational design and automation are being applied to Body-in-White development in automotive production.

On the architecture and built environment side, Hao (Richard) Zhang of Augmenta will present on functional AI for 3D design automation, with case studies including the first buildings in the world with AI-generated electrical systems.

Verena Vogler of McNeel Europe will introduce a new ecological simulation framework for Rhino and Grasshopper.

Claudia Valverde of the University of Stuttgart’s IntCDC will present on architected porous structures designed to support thermal comfort for cavity-nesting wild bees in building envelopes, which is either a very niche research topic or a preview of where performance-driven design for and with autonomous agentic AI is headed. Possibly both.

Other confirmed speakers include representatives from Siemens Digital Industries, SimScale, ToffeeX, Synera, Gravity Sketch, Fraunhofer IGD, Tech Soft 3D, Saxion Hogeschool, Compute Maritime, BeyondMath, Cognitive Design Systems, Istari Digital, Pasteur Labs, Rafinex, Generative Engineering, Metisec, Romantic Technology, AiA Life Designers, Palace 3D, and David Burpee Design + Sequence Soles.

Day one of the Barcelona event closes with a networking session on the roof deck overlooking the ocean.

The full schedule is at cdfam.com/barcelona-2026.

Register Today

Discounted registration is €800 and closes today, March 15. Standard registration is €1,000 and is available until April 5.

Academic registration is €450 and also closes April 5. Group rates are available.

Contact info@cdfam.com for invoicing, direct transfer, or group discount requests.

Register at cdfam.com/register.

Register to Attend

Student Volunteers

We are still accepting student volunteer applications for CDFAM Barcelona.

Volunteers assist with event logistics across both days and receive full access to the program in exchange.

Roles include attendee check-in, session support, technical setup, documentation, and AV support during the sessions.

If you are a current student in design, engineering, architecture, or a related field, and you are available for both days, this is a fantastic way to attend a professional symposium that would otherwise cost €800. We do not cover transport or accomodation, but you will receive a limited edition t-shirt and our eternal thanks.

Apply at cdfam.com/crew.

Ticket Giveaway

The tag-a-colleague giveaway also closes today.

Head to the CDFAM LinkedIn post, tag a colleague in the comments. If you both follow CDFAM, you are both entered to win complimentary registrations.

Enter as many times as you like. The winner is drawn today.

Giveaway post: linkedin.com/feed/update/urn:li:activity:7438951785626685440

This edition of the CDFAM Careers Board includes organizations presenting at CDFAM Barcelona, April 8-9. Posting on the board is a benefit included with a speaking slot, and it serves a practical purpose: presenters get direct visibility with an engaged, expert audience, and candidates get early access to the teams and individuals doing the work before those roles are widely circulated elsewhere.

The following Barcelona presenters all have open roles on the board right now: Airbus, PhysicsX, nTop, BeyondMath, NIKE, ARENA-AI, Pasteur Labs, Emmi AI, Compute Maritime, Istari Digital, Tech Soft 3D, and Cognitive Design Systems.

See All Open Roles

Software and Platform Engineering

nTop, PhysicsX, and Divergent are hiring across software and platform engineering roles in New York, London, and Torrance, CA. Positions range from infrastructure and workload orchestration at nTop, to AI Workbench and Simulation Workbench engineers at PhysicsX, to a new grad Software Engineer with a mechanical engineering focus at Divergent. Bench is looking for a Founding Engineer in Computational Geometry in London.

Computational Design and Architecture

OXMAN, Heatherwick Studio, Ennead Architects, Foster + Partners, Lithium Designers GmbH, and Decibel ASD all have computational design openings across New York, London, and Germany. Autodesk has posted a Distinguished Architect role in Portland focused on Building Design Products and Desktop Transformation.

Simulation and AI/ML Engineering

PhysicsX has an extensive range of simulation, CFD, FEA, machine learning, and forward-deployed engineering roles across London, Singapore, and New York. BeyondMath, Emmi AI, and Pasteur Labs have simulation-focused roles open in London, and remotely. AVEVA, Thales, and ENSIA EXPERT have industrial AI and simulation roles in Boston, France, and Madrid. Airbus has multiple engineering roles in Getafe.

Generative and Computational Design for Product

NIKE has multiple roles open spanning generative design, computational design, and 3D footwear across Beaverton and broader innovation functions. Under Armour and Brooks Running are also hiring 3D footwear designers in Portland and Seattle.

Maritime, Defense and Deep Tech

Compute Maritime is hiring across naval architecture, machine learning, and full stack development. Istari Digital has several roles open spanning digital engineering, software, and machine learning. ARENA-AI has a broad range of electrical engineering, simulation, and software roles posted.

Data and Infrastructure

SOM, Arup, Atomic Machines, and Allen Control Systems have data, infrastructure, and innovation-focused roles open across Chicago, Frankfurt, Emeryville, and the broader US.

Research and Academic

ETH Zurich has a Research Engineer position open in Zurich. Zahner has a Research and Development Internship in Kansas City.

See All Open Roles

All roles are listed in full on the CDFAM Careers Board. If you have a position to promote to the community, submit it directly via the job posting form on the site.

There is no other event where you will find this concentration of organizations, spanning engineering AI, physics-native simulation, generative design, computational architecture, and advanced manufacturing software, all in the same room, all at the frontier of their respective fields, and evidently all looking to hire.

CDFAM Barcelona is two days. The program is focused, the group is small, and the access is direct.

If you are navigating a career move or looking to build relationships with the teams doing the most interesting work in computational design and engineering AI right now, this is where to be.

See Full Program for CDFAM Barcelona

Register to Attend

The event is now just over a month away, April 8-9, at the Barcelona Biomedical Research Park on the Mediterranean waterfront.

The program is largely set. What follows is a section-by-section overview of what to expect you can see the current schedule, subject to minor changes.

The organizing idea behind this year’s program is one that runs through CDFAM as a series: computational design as a discipline of building systems to solve design problems.

The Barcelona program is structured to bridge systems-level engineering and decisions made at the part and material scale.

Full program and speaker details are at cdfam.com/barcelona-2026.

Breaks are on the outdoor deck at the PRBB, directly on the Mediterranean waterfront. The food is good. The views help.

Tickets are available at cdfam.com/register. Capacity is limited and the event historically sells out before the date, so if you are planning to attend, now is a great time to secure a spot.

Register to Attend

Program Overview

AI AND MACHINE LEARNING

A significant portion of the program addresses AI and machine learning from multiple angles - not just what the models can do, but how they are built, what data they require, and what it takes to deploy them in real engineering workflows.

PhysicsX will present their work moving from task-specific surrogate models toward Large Physics Models for production aerodynamics workflows. BeyondMath will argue for a different approach entirely - foundational physics AI trained on self-generated, first-principles data rather than customer simulation data, with case studies from motorsport and energy. EMMI AI will present NeuralMould, their commercially deployed Large Engineering Model for injection moulding, consolidating geometry processing, physics prediction, and post-processing into a unified interface. ARENA.AI will discuss foundation model development for electromagnetism, targeting electronic hardware design across semiconductor, aerospace, and automotive sectors. Pasteur Labs will present their perspective on simulation intelligence and where the field is heading.

DATA, SYSTEMS, AND WORKFLOWS

Getting AI into engineering practice requires more than models - it requires systems, data infrastructure, and workflow integration. This section of the program addresses that directly.

Tech Soft 3D will present HOOPS AI, a framework for correlating CAD geometry with manufacturing behavior and business process information. The approach transforms CAD and manufacturing data into unified, AI-ready representations that can bridge engineering and non-engineering domains without dependence on native CAD kernels or proprietary data models - enabling AI systems to reason across design, manufacturing outcomes, and operational drivers within a single coherent architecture. Istari will address the infrastructure problem from a different angle: secure, decentralized access to engineering data, enabling teams to work live from source data and collaborate in real time without surrendering data control. Quix will present their platform for automating R&D data analysis - consolidating test data into a single repository, enabling custom analysis tooling, automated report generation, and sequential test execution, removing the manual overhead that slows engineering teams between simulation and decision. Synera will present their work on Body-in-White development using Synera MAS, demonstrating how computational design workflows can modernize and accelerate automotive engineering processes in collaboration with SEAT-CUPRA.

ARCHITECTURE, ENVIRONMENT, AND BUILT SYSTEMS

Augmenta will present their work on functional AI for 3D design automation in the built environment - from pathfinding to generative modeling for building construction, including the first buildings with electrical systems delivered by AI-powered generative design. McNeel Europe’s Verena Vogler will introduce Rhino.Ecologic, a new ecological simulation framework for Rhino and Grasshopper that integrates location- and time-specific species distribution, biomass, and biodiversity modeling into computational design workflows. AiA Life Designers will address environmental performance simulation at the earliest stages of architectural design, where decisions carry the greatest impact but feedback is typically absent. Claudia Valverde from the University of Stuttgart’s IntCDC will present research on architected porous structures designed around real-world climatic and ecological data, with working prototypes installed on actual buildings and monitored under outdoor conditions.

PRODUCT, PERCEPTION, AND HUMAN FACTORS

Not all of the program sits at the deep engineering end. Yuan Mu from Nike will address computational fabrication applied to textile design, embedding athlete motion data into parametric workflows for footwear and apparel. Palace will discuss colour perception within a computational design context. Gravity Sketch will address spatial interaction and spatial computing as a design interface. David Burpee will present the Sequence Dynamic Insole Generator - an automated Houdini-based toolchain that generates variable density infill toolpaths directly from biomechanics data, with custom pathfinding algorithms embedding print constraints into G-code to produce gradient compressibility profiles tuned to individual kinematics. Saxion University of Applied Sciences will present complementary work on personalized CPAP mask design, using 3D scan data, postural analysis, and pressure mapping to drive computational mask generation and silicone 3D printing at regional hospital scale.

Full program and speaker details are at cdfam.com/barcelona-2026.

Breaks are on the outdoor deck at the PRBB, directly on the Mediterranean waterfront. The food is good. The views help.

Tickets are available at cdfam.com/register. Capacity is limited and the event historically sells out before the date.

Register to Attend

Her work introduces Rhino.Ecologic, a new ecological simulation framework built for Rhinoceros 3D and Grasshopper that embeds plant community modeling, biodiversity analysis, and biomass simulation directly into computational workflows.

Rather than treating ecology as a downstream validation exercise, Rhino.Ecologic integrates environmental intelligence directly into iterative design processes. Geometry is voxelized, environmental layers are mapped, and stochastic plant population dynamics unfold across yearly time steps, producing structured, ML-ready datasets within the same environment where designers are already working.

As Verena explains:

“Unlike traditional ecological assessment tools that operate as external post-processing software, Rhino.Ecologic embeds ecological simulation directly into parametric modeling workflows, preserving full geometric and data interoperability.”

The framework is currently in alpha testing with more than 100 participants across 60 institutions worldwide, approximately 85% from the AEC industry and the remainder from academia.

Developed by an interdisciplinary team of architects, computational designers, and a computational ecologist, the system bridges ecological science and computational design engineering.

At its core is a shift in mindset:

“In ecological modeling, we do not design individual behaviors directly; instead, we define environmental gradients, resource fields, and interaction rules, and observe how local interactions scale into emergent spatial patterns.”

This approach opens the door to new workflows where biodiversity, biomass, and habitat quality become measurable and dynamic design parameters.

“Rather than assessing environmental impact at the end of a project, we see a future where biodiversity, biomass, and habitat quality become active drivers within parametric workflows.”

In the full interview, we dive deeper into the voxel-based data architecture, the Joschinski Model for plant community simulation, machine-learning integration, and real-world applications, including its use in advanced computational design research at the Architectural Association in London.

Read the full interview on the CDFAM website.

Read Full Interview

Join us at CDFAM Barcelona to learn more about this work and connect in person with Verena and others advancing computational design, AI and machine learning for engineering and architecture

See the Full Program

Can you introduce Compute Maritime and explain what you’ll be presenting at CDFAM in relation to NeuralShipper and its role in generative AI for ship design?

Compute Maritime is a UK-based deep tech company building the next generation of AI-native design tools for the maritime industry. Our flagship platform, NeuralShipper, is the world’s first generative AI co-pilot specifically developed for ship design, optimisation, and simulation-ready engineering workflows.

At CDFAM, we will be presenting how NeuralShipper introduces a new computational design paradigm for maritime: instead of relying on slow, manual parametric modelling, engineers can generate thousands of high-performance vessel concepts within minutes, directly from a small set of specifications.

What makes this particularly relevant to the CDFAM community is that NeuralShipper is built around a Large Geometric Foundation Model that produces CAD-native outputs, primarily as valid NURBS surfaces, enabling immediate downstream simulation and manufacturability. It is a practical example of how generative AI can transform one of the most conservative engineering sectors while addressing sustainability at scale.

You describe NeuralShipper as a generative co-pilot for maritime systems. What types of inputs does it require, and how are user-defined constraints and performance criteria handled in the design process?

NeuralShipper is designed for early-stage concept exploration, so it requires only minimal inputs to begin generating meaningful design candidates.

Typically, users provide high-level specifications such as vessel type, principal dimensions, displacement targets, speed requirements, operational constraints, and sometimes mission-specific objectives like fuel efficiency or seakeeping priorities.

From there, the platform allows designers to define custom constraints and performance criteria, which are integrated directly into the generation and optimisation loop. This means NeuralShipper does not simply generate random shapes, it generates candidates that satisfy engineering feasibility and are aligned with the designer’s intent.

The result is a human-in-the-loop workflow where AI accelerates exploration, but the naval architect remains in control of design direction and decision-making.

Read the Full Interview

Register to attend CDFAM Computational Design Symposium in Barcelona to connect with Shahroz Khan and other leaders applying AI and machine learning in engineering and architecture. Join the discussion on practical computational design methods, simulation-driven workflows, and the future of AI-augmented design tools.

Organization:
MIT

Presenter:
Alfonso Parra Rubio


Crease, Fold, Transform.
Presentation Abstract
Folding is a fundamental process found throughout nature on multiple scales. Rather than altering the material itself, folding transforms its shape, offering a powerful means of engineering without compromising integrity.

This presentation explores, from an engineering and design perspective, the unique potential of folding and discrete assembly as a design and manufacturing tool across multiple scales in engineering.

From millimeter-scale bulk cellular materials to meter-scale structural corrugations and actuated robotic systems, and ultimately to architectural shell structures spanning tens of meters, folding enables the creation of high-performance, architected materials.

Speaker Bio
Alfonso Parra Rubio is a PhD candidate at the Massachusetts Institute of Technology, working at the Center for Bits and Atoms led by Neil Gershenfeld. His research explores how folding and discrete assembly can be combined to design and manufacture architected materials across multiple scales: from bulk cellular materials (millimeters to centimeters), to structural corrugations and actuated systems (centimeters to meters), and up to architectural-scale shell structures (meters to decameters). His work fundamentally explores how materials and structures are designed, engineered, manufactured, and assembled. In addition to his academic research, he founded RnKolektive, a collaborative platform for sculptural exploration. This parallel practice focuses on mixed-media works that merge folding techniques with blown glass, creating pieces that use the same research contributions but with an expressive intention.

Organization

Princeton University

Presenter:

Tuo Zhao

Super-Modular Chiral Origami Metamaterials
Presentation Abstract
Metamaterials with multimodal deformation mechanisms resemble machines, especially when endowed with autonomous functionality. A representative architected assembly, with tunable chirality, converts linear motion into rotation (1). These chiral metamaterials with a machine-like dual modality have potential use in areas such as wave manipulation, optical activity related to circular polarization and chiral active fluids. However, the dual motions are essentially coupled and cannot be independently controlled. Moreover, they are restricted to small deformation, that is, strain ≤2%, which limits their applications. Here we establish modular chiral metamaterials (2), consisting of auxetic planar tessellations and origami-inspired columnar arrays, with decoupled actuation. Under single-degree-of-freedom actuation, the assembly twists between 0° and 90°, contracts in-plane up to 25% and shrinks out-of-plane more than 50%. Using experiments and simulations, we show that the deformation of the assembly involves in-plane twist and contraction dominated by the rotating-square tessellations and out-of-plane shrinkage dominated by the tubular Kresling origami arrays. Moreover, we demonstrate two distinct actuation conditions: twist with free translation and linear displacement with free rotation. Our metamaterial is built on a highly modular assembly, which enables reprogrammable instability, local chirality control, tunable loading capacity and scalability. Our concept provides routes towards multimodal, multistable and reprogrammable machines, with applications in robotic transformers, thermoregulation, mechanical memories in hysteresis loops, non-commutative state transition and plug-and-play functional assemblies for energy absorption and information encryption.

References:
(1) Frenzel, T., Kadic, M. & Wegener, M. Three-dimensional mechanical metamaterials with a twist. Science 358, 1072–1074 (2017).
(2) Zhao, Tuo (presenter), Dang, X., Manos, K., Zang, S., Mandal, J., Chen, M., & Paulino, G. H. Modular chiral origami metamaterials. Nature, 640(8060), 931-940 (2025).

Speaker Bio
Tuo Zhao is a postdoctoral research associate at Princeton University. His expertise is in computational mechanics, nonlinear topology optimization, soft robotics, and mechanical metamaterials. Tuo is currently addressing the scalability challenge for developing useful metamaterials. By integrating an untethered actuation scheme (e.g., three-dimensional magnetic fields and micro-magnetic responsive materials), he designs micro-robotic machines with tunable properties on demand.

Organization:
STILFOLD

https://www.stilfold.com/

Presenter:
Julia Hannu



Greener by Every Fold. Strength in Every Curve.
Presentation Abstract
This talk introduces STILFOLD’s innovative origami-inspired manufacturing process, where metal sheets are folded into form. The process uses both straight and curved crease folding, expanding the possibilities of how sheets can be transformed into products. This, to make curved crease folding accessible to a wider community of designers and engineers – moving it from a niche research technique into a scalable industrial method. Our aim is to develop a more environmentally friendly way of making things – reducing the number of parts, energy consumption, material use and transportation needs. Achieving this involves multiple layers of complexity: from designing folding patterns of efficient structures to developing dedicated folding systems for production at scale.

The presentation will share insights into how STILFOLD is pushing to transform folding into a sustainable and practical approach to manufacturing – and what that could mean for the future of design, engineering, and production.

Speaker Bio
Julia Hannu is a Software Engineer and Computational Design Lead at STILFOLD, where she develops digital tools and algorithms to enable new approaches to sustainable manufacturing and design. Her work centers on transforming complex geometric challenges into practical, efficient, and user-friendly solutions. With a background in architecture and an MSc in Architectural Computation from UCL, she combines experience from practice and academia to bridge technology, design, and sustainability.

Organization

Tetmet

https://www.tetmet.net/

Presenter:

Rachel Azulay

Conformal Lattice Design Made Easy: A CAD-Integrated Approach
Presentation Abstract
TETMET has developed an innovative process to produce large-scale lattice structures in an automated way, enabling applications across multiple industries.

However, existing lattice design software has significant limitations, particularly when it comes to creating efficient, manufacturable conformal lattice structures. Most available tools were developed with general 3D printing in mind, offering only basic latticing capabilities that fail to meet the demands of more advanced applications.

Our approach takes a different path by integrating lattice design seamlessly into traditional CAD workflows. By combining the flexibility of CAD with the specific requirements of lattice generation, we significantly enhance the design process—allowing engineers to work with familiar tools while unlocking new possibilities for complex, high-performance structures.

Speaker Bio
Rachel holds a PhD in Lattice Structure Design and leads the Application Engineering team at TETMET. She specializes in transforming complex customer challenges into innovative, lightweight lattice solutions, bridging cutting-edge research with real-world applications.

Organization

Scawo3D

Presenter:

Philip Schneider + Timo Zollner

Computational Design for Assembly: Automating Design Workflows for 3D Concrete Printed Freeform Staircases
Presentation Abstract
Building large freeform reinforced concrete staircases has always been a challenge. Traditional methods rely on labor-intensive wooden or EPS formwork, making many designs too expensive. This can be changed with Selective Paste Intrusion, a new 3D concrete printing technique by Scawo3D using a large particle bed, with no constraints related to print overhangs or angles.

While fabrication now allows full geometric freedom, the design process became the bottleneck. Our previous AutoCAD-based solution, initially developed for producing G-codes for CNC-milling EPS formwork blocks, was not viable for 3D printing. Manual 3D modeling made scaling production impossible, leaving the printer underused. To solve this, Timo Harboe Zollner developed an automated workflow that cuts design time by up to 95%. This approach balances automation with intuitive user input, transforming 2D geometry into finely detailed 3D models in minutes. It integrates SubDs, meshes, volumetric modeling, and implicit modeling, achieving in moments what once took days.

This presentation highlights the adaptation of computational design to a new production method—one with only few geometric constraints yet capable of achieving material properties comparable to standard concrete.

Speaker Bio
Philip Schneider Computational & Architectural Design Lead at Scawo3D and founder of Skeno. He holds a M.A. from TU Munich with a focus on computational methods in architecture and specialises in 3D concrete printing by Selective Paste Intrusion at an architectural scale. Since 2022, he has led the design and fabrication of the first projects realised by SPI in academia and industry.

Timo Harboe Zollner is the founder of Timo Harboe ApS, a Copenhagen-based consultancy specializing in automating processes related to geometry, particularly within additive manufacturing. With a background in structural engineering and computational design, Timo collaborates with clients to develop parametric workflows and digital tools that streamline complex design and fabrication processes. His recent projects include automating the generation of 3D-printed formwork for freeform concrete staircases together with Scawo3D

About CDFAM:
CDFAM is a global symposium series at the forefront of computational design, advanced manufacturing, and performance-driven engineering. With a strong emphasis on innovation, CDFAM highlights how leading companies and researchers are leveraging AI, machine learning, and simulation technologies to drive the next generation of design tools, workflows, and digital fabrication methods.

The symposium fosters cross-disciplinary collaboration and knowledge exchange between designers, engineers, and technologists exploring the cutting edge of digital design — from generative workflows.

Past presenters and partners include companies such as NVIDIA, NASA, New Balance, BMW, ARUP, Foster +, Partners, BIG, Autodesk, Dassault Systèmes, nTopology, PyhicsX, Neural Concept, Siemens and more, showcasing how computation and AI are transforming everything from aerospace to footwear.

Learn more at

https://cdfam.com