AIML - Machine Learning Research Lead, RL Agents, MLR
Core
Lead research on reinforcement learning and post-training for agentic AI, managing a small team of senior researchers.
Role type
Senior IC research lead (RL & post-training)
Builds
Interactive agents with tool-calling, coding, and long-horizon capabilities
Domain
Artificial Intelligence / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement learning, post-training, agentic AI, synthetic environment generation, ML infrastructure, team leadership, hands-on coding
Preferred skills
Efficiency-aware modeling, open-endedness, evolutionary computation, multi-agent systems, theoretical RL grounding
Technologies
Large language models, self-supervised learning, generative models
Responsibilities
Lead research on RL and post-training for agentic capabilities; Build and own synthetic data and task-generation pipelines; Drive codebases and infrastructure for the core RL research effort; Manage and mentor a small team of senior researchers; Stay hands-on with experiments and code; Connect post-training research to efficiency and deployment constraints; Collaborate on adjacent directions like world models and self-improvement; Publish in top venues and engage with the research community.
