About me
AI that expands what
humans can imagine.
I build computational tools that help people make better decisions in complex, uncertain worlds — from urban climate planning to molecular design. Research is only useful when it reaches the people who need it.
Currently working on
CytoTransport
In-silico modeling of cellular transport mechanisms — ion channels, transport proteins, and their role in disease. Bridging biomedicine, computational modeling, and structural biology.
See the project
OpenSKIZZE
Surrogate-assisted quality diversity optimization generates thousands of diverse building layouts, each evaluated for cold airflow impact without CFD simulation. A UMAP model reveals which designs cluster by airflow behaviour.
See the project
Neue Stadtgärtnerei
A grassroots initiative in Bonn-Dransdorf creating a climate-resilient space for housing, agroforestry, and environmental education — on the site of the old city nursery.
See the projectWhy I do this
Optimization and machine learning should expand human understanding, not automate human judgment away. The best tools I can build are ones that show people options they couldn't have imagined alone — and then let them choose. That means embracing uncertainty, keeping requirements open, and treating the iterative process of design as something to support, not shortcut.
Real problems don't fit neatly into papers. That's why I work across computational fluid dynamics, molecular force fields, urban planning, and community organizing. The methods transfer. The stakes are always real.
Recent writing