I work on RL, LLMs, and their interactions at Cohere. Previously, I was a research scientist at InstaDeep, where I focused on using transformers for combinatorial optimization and discrete problems. I hold a Ph.D. in reinforcement learning for combinatorial optimization from Inria/CNRS, where I was part of the SequeL/ScooL team under the supervision of P. Preux.
Technical Staff, 2024-2023
Cohere
Research Scientist, 2023-2024
Instadeep
PhD Student, 2019-2023
Inria Lille, SequeL/ScooL team