Robot Learning Engineer - Manipulation

What you'll do

• Own the manipulation learning loop from task definition and demonstrations through training, real-robot evaluation, and deployment.
• Train and fine-tune policies, diagnose failures, and improve data, models, and evaluation using robot performance measures.
• Deploy policies on edge compute and package reusable models and task recipes.

What they ask for

• 1+ years of professional experience.
• Bachelor's degree in Computer Science, Software Engineering, or equivalent.
• Have trained or fine-tuned a learned manipulation policy and deployed and evaluated it on a physical robot.
• Strong Python and PyTorch skills, practical depth in imitation learning and at least one modern policy family, plus working knowledge of robot kinematics, coordinate frames, camera calibration, and low-level control interfaces.

Nice to have

• Experience with bimanual manipulation, force-controlled insertion, tactile sensing, or dexterous hands.
• Experience with ROS 2, LeRobot, Isaac, or MuJoCo.

Pay

$150K – $300K USD base salary

Tools

Python, PyTorch, vision-language-action models, diffusion policies, action-chunking transformers, ROS 2, LeRobot, Isaac

AI focus

Train and fine-tune manipulation policies, including pretrained vision-language-action models and task-specific policies, and deploy and evaluate them on physical robots.