Team
The AI Safety & Interpretability Lab is currently being established. This page will be updated as soon as new members join.
Lukas Galke Poech
Associate Professor, Head of the Group
Lukas Galke Poech is an Associate Professor in the Department of Mathematics and Computer Science at the University of Southern Denmark. His research focuses on advancing AI safety through interpretability. He is the principal investigator of the MIST Project on Scalable Mechanistic Interpretability for Safe and Trustworthy Language Model Agents, funded by the Novo Nordisk Foundation. Lukas received his PhD in representation learning from Kiel University, Germany. He then joined the Max Planck Institute for Psycholinguistics as a postdoc, where he worked on emergent communication and took inspiration from research on how language works in the human brain to fuel his research on understanding learning, behavior, and cognition in language models.
Email | Website | GitHub | Google Scholar | LinkedIn
Anton Danholt Lautrup
Postdoc (since February 2026)
Annemette Brok Pirchert
PhD Student (since February, 2026)
Filippo Tonini
PhD Student (since March 2026)
Danial Namazifard
PhD Student (since May, 2026)
| Google Scholar |
Gianluca Barmina
PhD Student (since 2025)
Federico Torrielli
Guest PhD Student (Apr-Jun 2026)
William Brach
Guest PhD Student in 2025, now latent collaborator