Robotics Engineer - Humanoids focus

Responsibilities

• Train and deploy reinforcement learning and imitation learning policies for real-world humanoid locomomanipulation tasks.
• Design high-fidelity simulation environments to improve sim-to-real transfer and accelerate iteration.
• Define research goals based on practical engineering considerations.
• Design experiments, write reusable code, evaluate models, and organize results.
• Contribute to research publications and open-source efforts.
• Partner with the robot deployment team to ship policies to production customer sites and own the pipeline from research through deployment.

Requirements

• Bachelor's degree in computer science, computer engineering, or a relevant technical field, or equivalent practical experience.
• Research experience in machine learning, robotics, and computer vision.
• Experience developing robotics algorithms or machine learning models at scale.
• Programming experience in Python or C++ and familiarity with PyTorch or JAX.
• Must be currently based in and authorized to work in the United States and maintain ongoing work authorization during employment.
• Master's or PhD in robotics, computer science, computer engineering, or a relevant technical field is preferred.
• Preferred experience includes robotics, computer vision, or machine learning research; first-author publications at peer-reviewed AI or robotics conferences; high-fidelity simulation; humanoid policy training and deployment; computer vision, sensors, 3D data, segmentation, tracking, and detection; domain randomization; reward shaping; sim-to-real engineering; and real-world deployment of proprioceptive and visual humanoid policies.

Benefits

• Work on physical AI and humanoid robotics research spanning simulation, deployment, and customer-site production use.
• The role is based in Redmond, Washington, and is open to candidates currently based in and authorized to work in the US.