Reinforcement Learning Scientist

We are developing a quantitative decision-making foundation model designed for data-efficient, safe, and robust deployment across industries such as logistics, biotechnology, and retail. Built on advanced meta-reinforcement learning, our model learns to master thousands of diverse environments and can be rapidly adapted to clients' data for high-performance, real-world decision making.We are seeking a Reinforcement Learning Scientist to join our Lab team. In this role, you will work at the intersection of research and engineering—improving our core algorithms, building high-quality training pipelines, and contributing production-grade code that advances the capabilities of our foundation model.Minimum Requirements: PhD in Reinforcement Learning, or a Master’s degree with few years of research or industry RL experience Strong programming skills, particularly in Python and Pytorch  Ways to stand out: Hands-on experience deploying RL in real-world applications Background in meta-reinforcement learning Experience training large transformer models (LLMs or similar)  Demonstrated work through open-source or personal GitHub projects Publications in top-tier ML conferences (NIPS, ICML, ICLR, ...) Fluency in French is a bonus