Research focus, teaching, and student supervision
My work spans two areas. In probabilistic machine learning I build fast, scalable Bayesian inference tools: I founded and lead the open-source RxInfer ecosystem (RxInfer.jl and its supporting libraries), used in academia and industry for real-time, reactive inference. In computational immunology I co-led the development of VDJdb, a curated T-cell-receptor database behind a Nature Methods paper and still used by researchers worldwide.
I contribute to the national AiM-TT initiative on AI for multi-modal traffic and transport, working with TU Delft and the Nationaal Dataportaal Wegverkeer (NDW).
Full paper list · 2,778+ citations · Nature paper · dissertation
Recorded conference talks, tutorials, and podcast appearances
The open-source RxInfer ecosystem and other projects
MSc course, ~100 students
From September 2026 I support this MSc course, helping students master probabilistic modelling and message-passing inference.
Core course (5ARA0) that grew from ~70 to 200+ students
Supported students at the intersection of software practice and AI during my PhD, as the course scaled to its current size.
RxInfer documentation, tutorials, and 40+ worked examples
I treat my open-source work as teaching at scale: the documentation, tutorials, and 40+ worked examples I wrote for the RxInfer ecosystem are used by students, researchers, and practitioners worldwide to learn Bayesian inference. I also present regularly at conferences and on podcasts, and enjoy building interactive demos.
Day-to-day / co-supervision; several projects shipped as open-source packages
I co-supervise PhD students and have supervised MSc projects, on a day-to-day basis (formal promotorship sits with senior staff). I deliberately steer projects toward results that ship and that others can build on.
PyData & JuliaCon Eindhoven; talks, podcasts, and tutorials
I help build the local research-software community and speak widely about probabilistic programming.