Staff Reinforcement Learning Research Engineer

Skills

About the Role

You will own and develop the reinforcement learning stack for humanoid and quadruped robots. You will implement learning algorithms, scale GPU-accelerated simulation, improve sim-to-real transfer, integrate reinforcement learning with multimodal policies, deploy policies to robots, and build visualization tools for data-driven research.

Requirements

• MS with 3+ years of experience or a PhD in machine learning, robotics, or a related field
• Experience deploying policies on physical robots with attention to latency, robustness, and safety
• Expertise with RL toolboxes including RSL-RL, CleanRL, RLlib, or Stable Baselines
• Expertise with simulation and rendering tooling including Isaac Lab, MuJoCo, MjWarp, or MjLab
• Proficiency in PyTorch or JAX and inference runtimes including ONNX, Triton, or TensorRT
• Strong software fundamentals in Bazel, monorepos, Docker, and CI/CD

Responsibilities

• Implement on-policy and off-policy learning algorithms
• Scale GPU-accelerated simulation to generate millions of samples per second
• Develop sim-to-real policies that transfer to physical robots
• Integrate reinforcement learning with VLAs to fine-tune and distill multimodal policies
• Make policy deployment easy, fast, and reproducible
• Build visualization tools for data-driven research

Benefits

• Medical insurance
• Dental insurance
• Vision insurance
• 401(k)
• Paid time off
• Annual bonus structure