Senior Research Scientist FMTA

Design, implement, and deploy reinforcement learning and post-training research for large (multi-modal) language models, bringing innovations into production. Build and scale RL pipelines, align models with human intent to enable reasoning and improved performance, safety, and efficiency, and manage the full lifecycle from ideation and modeling through ablations and deployment. Collaborate with Engineering, ML Platform, and HPC teams and partner with academic/industrial collaborators.