Whole-Body Control & Safe Reinforcement Learning Engineer
Humanoid is the first AI and robotics company in the UK, creating the world’s most advanced, reliable, commercially scalable, and safe humanoid robots. Our first humanoid robot HMND 01 is a next-gen labour automation unit, providing highly efficient services across various use cases, starting with industrial applications.
Our Mission
At Humanoid we strive to create the world’s leading, commercially scalable, safe, and advanced humanoid robots that seamlessly integrate into daily life and amplify human capacity.
About the Role
We are looking for a Senior or Staff Robot Control Engineer to develop whole-body control systems for bipedal robots.
You will work on a control stack combining whole-body and reinforcement learning, enabling robust loco-manipulation behaviors on real robots. A central focus of the role is ensuring that learning-based policies operate safely within structured control architectures, maintaining stability, predictability, and reliable deployment on hardware.
You will design and deploy control algorithms that run directly on physical robots, iterating between simulation and hardware experiments. You will also help shape the architecture of the robot control stack, defining how learning-based policies integrate with whole-body control and safety mechanisms.
The problems you will work on include dynamic locomotion, contact-rich manipulation, balance recovery, and safe integration of learning-based behaviors.
You will collaborate closely with robotics engineers across Boston, London, and Vancouver working on robot design, locomotion, manipulation, and robot deployment..
What You’ll Do
- Design safe whole-body control architectures for bipedal robots.
- Develop controllers enabling stable locomotion and loco-manipulation.
- Integrate reinforcement learning policies within the control stack, ensuring safe operation and reliable hardware behavior.
- Define interfaces between learned policies and structured controllers, enabling supervision and fallback mechanisms.
- Validate controllers in simulation and on physical robots.
- Contribute to a robust, modular real-time control codebase.
We’re Looking For:
- MS or PhD in Robotics, Control, Computer Science, or a related field.
- Experience developing control systems for complex robots, ideally legged or humanoid platforms.
- Experience with whole-body control or physics-based robot control architectures.
- Experience implementing reinforcement learning for robotic systems.
- Strong understanding of robot dynamics, kinematics, and multi-contact interaction.
- Strong C++ development skills for real-time robotic systems.
Nice to have
- Experience with bipedal locomotion or loco-manipulation.
- Experience with safe RL approaches (e.g., constrained RL, safety filters, supervised policies).
- Background in trajectory optimization, motion generation, or MPC.
- Experience with real-time robotics middleware (e.g., ROS2).
What We Offer
- Competitive salary plus participation in our Stock Option Plan.
- Paid vacation with adjustments based on your location to comply with local labor laws.
- Travel opportunities to our Boston and Vancouver offices.
- Comprehensive health insurance coverage.
- Freedom to influence the product and own key initiatives.
- Collaboration with top‑tier engineers, researchers, and product experts in AI and robotics.
- Startup culture prioritising speed, transparency, and minimal bureaucracy.
How to Apply
Does this role sound like the perfect fit for you?
Fill in the form and include links or files that showcase the best of what you’ve built and achieved.
About Humanoid
Humanoid is a London-based robotics company creating commercially scalable humanoid robots for industrial automation. Founded by serial entrepreneur Artem Sokolov, the company has built the HMND 01 platform featuring 29 active degrees of freedom and AI-driven end-to-end reasoning. Its robots target warehouses, logistics hubs, and retail facilities through a robotics-as-a-service (RaaS) model. The company conducted a landmark trial at the Siemens Electronics Factory in Erlangen achieving 60 tote moves per hour with over 90% autonomous success rate. The team of 200+ includes alumni from Apple, Tesla, and Boston Dynamics. Preparing for a Series A round.