Postdoctoral Researcher (PhD) - FAIR - Core Learning

Description du poste:

Meta's Fundamental AI Research (FAIR) organization is seeking a postdoctoral researcher to drive advancements in generative models, with a particular focus on Reinforcement Learning in large language models (LLMs) and/or formal math (Lean).
Innovate, lead, and execute pioneering research to push the state-of-the-art in generative models and LLM performance Systematically perform independent research, quickly adapting to new developments in the field Directly contribute to the experimental process, including designing details, implementing reusable code, running evaluations, and organizing results Contribute to publications, open-sourcing initiatives, and mentor other team members Ensure effective cross-functional collaboration

Profil requis du candidat:

Currently possess or be pursuing a PhD in Computer Science, Mathematics, or a similar quantitative discipline Demonstrated experience with training, fine-tuning, and experimentation on foundation models beyond black-box usage Must be able to obtain and maintain work authorization in the country of employment Expertise in RL for LLMs and/or Lean (formal mathematics) Holds first-author publications at peer-reviewed AI conferences (e.g., NeurIPS, ICML, ICLR)