Senior Robot Learning Engineer

📋 Description

• Own how LightSpeed's robots learn and perform physical skills: build the data pipeline that
• Define how we capture demonstrations: teleoperation rigs (leader arms, VR) and egocentric capture
• Set the policy architecture: a shared vision and force backbone with task-conditioned heads; train
• Own the execute executor: classical control and learned policies behind one contract; build the
• Co-own foundation interfaces with world sensing and agentic planning principals; for each new
• Set robot learning and control architecture across both robot families; lead and mentor learning

🎯 Requirements

• 5+ years in robotics or machine learning, including learned manipulation policies deployed on real
• Deep experience with imitation learning and reinforcement learning, and with when to use each.
• Force and impedance control for contact-rich manipulation.
• Built a data pipeline for robot learning: teleoperation capture, labelling, versioning and
• Deep learning in PyTorch, from dataset to deployed policy.
• Strong Python and C++.

🎁 Benefits

• Teach robots the trades that build homes and address the housing crisis.
• Own robot learning end to end, from demonstration capture to deployed policy.
• Shape the foundation every trade is built on.
• Work on rare real-world problems: deformable materials, contact-rich finishing, learning from human
• Hands-on culture with direct access to robots, sensors and manufacturing environments.
• Competitive compensation and comprehensive benefits.