Senior Member of Technical Staff: Reinforcement Learning for Policy Post-Training

You'll advance reinforcement learning for manipulation alongside a world-class team—using RL to push our robot policies on contact-rich, dexterous tasks beyond what imitation and supervised methods reach. Working hand in hand with the manipulation, controls, and simulation teams, you'll own the reward, curriculum, and algorithm design at the core of that work and help carry it through to results that hold up on real hardware doing real manipulation.

Responsibilities

• RL for Manipulation: Design and run RL for contact-rich manipulation, including reward design, on/off-policy methods, and stable training at scale.
• Sim-to-Real: Drive the RL side of sim-to-real for manipulation—domain randomization, system identification, and the iteration that makes policies transfer—working closely with the simulation team on the shared transfer loop.
• Closing the Loop: Combine simulation, offline data, and real-world feedback into manipulation policies that improve predictably rather than by luck.
• Reward & Task Design: Craft rewards, curricula, and task setups that make hard manipulation skills learnable without reward hacking.
• Collaboration & Mentorship: Partner with the manipulation, controls, and simulation teams, and mentor MTS engineers on the RL stack.

Requirements

• RL Depth: Strong hands-on RL experience with demonstrated results on hard, real-world, or large-scale problems.
• Manipulation: Experience applying learning to manipulation or contact-rich control (grasping, dexterous, or bimanual manipulation).
• Sim-to-Real: Demonstrated success transferring learned policies from simulation to physical robots.
• Ownership: Ability to design rigorous experiments and drive an ambiguous workstream independently to a result.
• Software Engineering: Strong fundamentals and comfort with large training/simulation codebases.

Preferred Qualifications

• Experience with dexterous hands, high-DOF manipulators, or bimanual systems.
• Familiarity with GPU-accelerated simulation for manipulation (Isaac, MuJoCo, etc.).
• Background in offline RL, learning from demonstration, or combining RL with imitation.

Benefits

• Competitive total compensation program, including salary, annual cash bonus, and company equity.
• Company-subsidized insurance programs.
• 401(k) with company match.
• Flexible PTO.
• Daily lunch.
• Other benefits.