Staff Reinforcement Learning Research Engineer
Core
Building scalable reinforcement learning frameworks for humanoid and quadruped robots, focusing on simulation, policy optimization, and on-robot deployment.
Role type
Staff Reinforcement Learning Research Engineer
Builds
Scalable RL stack, massively parallel simulation environments, and production-grade training pipelines for physical robots.
Domain
Robotics, Reinforcement Learning, Computer Graphics
Deliverable
production ML models
Required skills
Reinforcement learning algorithms (on-policy/off-policy), GPU-accelerated simulation, sim-to-real transfer, PyTorch/JAX, robotics control, software engineering fundamentals
Preferred skills
Production-grade RL pipeline experience, heterogeneous compute clusters, Kubernetes, VLAs and policy distillation
Technologies
RSL-RL, CleanRL, RLlib, Stable Baselines, Isaac Lab, MuJoCo, MjWarp, MjLab, ONNX, Triton, TensorRT, Bazel, Docker
Responsibilities
Implement on-policy and off-policy learning algorithms, scale GPU-accelerated simulation, integrate RL with VLAs, build visualization tools for data-driven research, ensure fast and reproducible deployment
Seniority
Staff, hands-on IC with strategic ownership
