Charbel-Raphaël Segerie

Logo

I am currently the executive director at CeSIA.

I work mainly on AI safety. I have organized and led the Turing Seminar, a course on AI safety in the MVA Master's program, and the bootcamps ML4Good. You can find here my recent work on AI safety, which focuses on RLHF and interpretability. I was TA in London for ARENA, in Berkeley for the MLAB, and CTO of Omnisciences. I've researched at Inria Parietal and Neurospin, and enjoy philosophy and jazz piano.

Here is my LinkedIn, Twitter, and Github.

Short Bio

Charbel-Raphael Segerie is the Executive Director of the Centre pour la Sécurité de l’IA (CeSIA) in Paris, where he leads research and education on AI safety. He teaches an AI safety course at the École Normale Supérieure, which is being developed into a textbook. His work focuses on identifying emerging risks in artificial intelligence, improving current safety methods such as RLHF and interpretability, and advancing safe-by-design AI approaches. Additionally, he contributes to AI evaluation efforts and collaborates on the EU AI Office’s Code of Practice for general-purpose AI systems. Charbel also founded ML4Good, a 10-day bootcamp designed to upskill researchers in AI safety.