AI researcher building next-generation language models. Founding Researcher at Isara Labs; tenured researcher at Inria.
I work on AI systems that learn from data and experience: large language models, reinforcement learning, and how to align them with human goals. I am a founding researcher Isara Labs, an AI startup, and remain a tenured researcher at Inria.
Research context
Michal is the Founding Researcher at Isara Labs, tenured researcher at Inria, and a lecturer at MVA at ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. He works on methods and settings that are able to deal with minimal feedback, such as deep reinforcement learning, bandit algorithms, self-supervised learning, or self play. Michal has recently worked on representation learning, world models and deep (reinforcement) learning algorithms that have some theoretical underpinning. In the past he has also worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. Michal is now working on a new generation of large language models (LLMs), in addition to providing algorithmic solutions for their scalable test-time inference, fine-tuning and alignment. He received his PhD in 2011 from the University of Pittsburgh, before getting a tenure at Inria in 2012 and co-creating Google DeepMind Paris with R. Munos. In 2024, he became a Principal Llama Scientist at Meta, building online reinforcement learning stack and research for Llama 3. In 2025, he joined Isara Labs as a founding researcher.
Domains
Build posts
Short, public updates on experiments, prototypes, validation, and next steps.
Deep experience in RL, LLM post-training, alignment, and large-scale research execution at the frontier (DeepMind, Inria). Strong network across European and US AI research, and operating experience as a founding researcher of an AI startup. Happy to advise on technical roadmaps, fundraising narratives, and research hiring.
Collaborations on hard frontier-AI problems (RL, alignment, agents, post-training). Conversations with investors and founders building serious AI infrastructure or research labs. Talented researchers and engineers interested in joining Isara Labs.
Mentor signal
Links
Browse public events around this profile's city and domains.
