Senior ML Research Engineer (Humanoid Robotics)

Location: London

Company

A robotics company developing intelligent humanoid robots through AI, machine learning, embodied AI, robotic locomotion, and intelligent automation.

What you will do

• Design and train reinforcement learning and imitation learning policies for robotic locomotion and whole-body control.
• Develop motion capabilities enabling humanoid robots to walk, balance, adapt, and interact with their surroundings.
• Build scalable simulation and training environments with Isaac Lab, Isaac Sim, MuJoCo, or similar platforms.
• Improve sim-to-real transfer and ensure learned behaviours perform reliably on physical robots.
• Deploy, evaluate, and optimise ML policies for real-time robotic control.
• Collaborate with robotics, simulation, autonomy, and engineering teams to integrate learning-based algorithms into robotic systems.

Requirements

• 3+ years of experience in machine learning research or engineering, ideally involving robotics or physical systems.
• Strong programming experience with Python and PyTorch.
• Hands-on experience with reinforcement learning, alongside imitation learning, generative models, or related approaches.
• Experience with physics-based simulation environments such as Isaac Lab, Isaac Sim, or MuJoCo.
• Strong understanding of deep learning, policy architectures, and model training.
• Degree in Robotics, Machine Learning, Computer Science, or a related technical field.

Nice to have

• Experience with humanoid robotics, legged locomotion, or whole-body control.
• Knowledge of sim-to-real transfer, domain randomisation, and motion imitation.
• Experience deploying learned policies onto physical robotic systems.
• Familiarity with motion capture, trajectory optimisation, or model-based control.
• Experience scaling reinforcement learning training across simulated environments.
• Publications at NeurIPS, ICML, ICLR, CoRL, or RSS, or contributions to relevant open-source projects.

Culture & Benefits

• Permanent, full-time position.
• Work on physical humanoid robots at the intersection of reinforcement learning, robotics, and control systems.
• Collaborate with a highly skilled team of researchers and engineers in a rapidly evolving robotics field.