Lead/Senior Research Scientist (Agentic RL)
Core
Advance the development of high-performance large language models (LLMs) for complex, high-stakes professional workflows through research in agentic reinforcement learning, model training, and evaluation.
Role type
Lead/Senior Research Scientist (Agentic RL)
Builds
Reliable, production-ready AI capabilities for planning, reasoning, tool use, and long-horizon task execution
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Agentic reinforcement learning, model training, model evaluation, continual learning, preference optimization, planning, reasoning, tool use, long-horizon task execution
Preferred skills
Shaping research roadmap, mentoring colleagues, representing the team in the machine learning research community
Technologies
Large open-weight models
Responsibilities
Conduct research and experimentation across agentic RL, model training, and model evaluation; Collaborate with research engineers, legal and tax experts, and product teams to translate research into model improvements; Shape the research roadmap and mentor colleagues at the Lead level