Jan Wehner

Jan is a Researcher on the Frontier Security team at IAPS.

Before joining IAPS, Jan was a Winter Fellow at the Centre for the Governance of AI. Previously, he was a PhD candidate at the CISPA Helmholtz Center for Information Security, where his research on LLM safety and interpretability was published at TMLR, NeurIPS, and EMNLP. Jan holds an MSc in Computer Science from TU Delft and a BSc in Business Informatics from the University of Bamberg. During his studies, he founded the Delft AI Safety Initiative and conducted research through the Pivotal Research Fellowship and AI Safety Camp.