About Me

I am a doctoral fellow at the ETH AI Center supervised by Prof. Dr. Andreas Krause and Prof. Dr. Giorgia Ramponi. My research focuses on (multi-agent) reinforcement learning, reinforcement learning from human feedback (RLHF), and active learning. In particular, I am interested in game theoretic formulations of optimization problems in these areas. Ongoing projects are centered around sample-efficient data collection in RLHF to reduce annotation costs for LLM post-training and optimizing for complex preference structures beyond reward models.

I was a core contributor and lead of the post-training team at the Swiss AI Initiative during the development of the open-source large language model Apertus.

If you are interested in working together, feel free to reach out to me via email.