23 days ago
London, United KingdomSenior / Staff+
Responsibilities
- Design and train reinforcement learning policies for humanoid robot control.
- Build scalable simulation and training pipelines using environments such as Isaac Lab and MuJoCo.
- Design reward functions, observation spaces, and curricula for complex robotic behaviors.
- Improve the robustness and sim-to-real transfer of learned policies.
- Deploy and evaluate learned policies on real robotic systems.
- Integrate learned policies into the robot control stack.
- Collaborate with controls and robotics engineers through iterative simulation and hardware experimentation.
Requirements
- MS or PhD in Robotics, Machine Learning, Computer Science, or a related field.
- Strong experience with reinforcement learning, including methods such as PPO, SAC, or offline RL.
- Experience applying reinforcement learning to robotics or physical systems.
- Experience deploying learned policies on real robotic systems.
- Experience with physics-based simulation environments such as Isaac Lab or MuJoCo.
- Strong programming skills in Python and/or C++.
- Preferred: experience with reinforcement learning for locomotion or legged robots, sim-to-real transfer, robot dynamics, control, or whole-body control.
Benefits
- 23 days of accrued annual leave, 15 days of paid sick leave, and paid company holidays.
- Fully funded private healthcare for UK employees, including virtual and in-person care and mental health and serious illness support.
- Equity participation.
- Pension scheme with an 8% total contribution: 5% employee and 3% employer.
- Free daily breakfast, catered lunch, and snacks in the office.
- Collaboration with engineers, researchers, and product experts in AI and robotics.
- Freedom to influence the product and own key initiatives.
- In-office work is referenced through the provided in-office meals and snacks.
Categories
ML EngineeringRobotics
