Reinforcement Learning Engineer - Locomanipulation

Humanoid; Greater London; Presencial; GBP 90.000 - 150.000; Tempo integral

Benefícios oferecidos por esta vaga

Annual leave

Private healthcare

Equity

Pension 8%

Meals in-office

Collaboration with engineers

Product influence

Resumo da vaga

Humanoid is seeking a Senior or Staff Reinforcement Learning Engineer to develop learning-based control policies for humanoid robots. You will design and train RL policies enabling dynamic locomotion and loco-manipulation on real robots, building scalable pipelines and improving sim-to-real transfer for reliable hardware deployment.

You will collaborate with controls and robotics engineers to integrate learned policies into the robot control stack, iterating between large-scale simulation and

Qualificações

• MS or PhD in Robotics, Machine Learning, Computer Science, or related field.
• Strong experience with reinforcement learning (e.g., PPO, SAC, offline RL).
• Experience applying RL to robotics or physical systems.
• Experience deploying learned policies on real robotic systems.
• Experience with physics-based simulation environments (e.g., Isaac Lab, MuJoCo).
• Strong programming skills in Python and/or C++.

Responsabilidades

• Design and train reinforcement learning policies for humanoid robot control.
• Build scalable simulation and training pipelines (e.g., Isaac Lab, MuJoCo).
• Design reward functions, observation spaces, and curricula for complex behaviors.
• Improve robustness and sim-to-real transfer of learned policies.
• Deploy and evaluate policies on real robotic systems.
• Integrate policies into the control stack.

Conhecimentos

Reinforcement learning

Python

C++

Robotics

Formação

MS or PhD in Robotics/ML/CS

Ferramentas

MuJoCo

Isaac Lab

Descrição da vaga

Here at Humanoid, we believe in a future where robots amplify human potential. That’s why we’ve set out on a mission to build the world’s most capable, commercially-scalable, and safe humanoid robots. We’re bringing that mission to life with HMND‑01 Alpha - our rapidly developed humanoid platform now running in real industrial pilots - and we’re growing the team to take it even further.

About The Role

We are looking for a Senior or Staff Reinforcement Learning Engineer to develop learning-based control policies for humanoid robots.

You will design and train reinforcement learning policies that enable dynamic locomotion and loco-manipulation behaviors on real robots. Your work will focus on building scalable training pipelines, designing reward functions and environments, and improving sim-to-real transfer for reliable deployment on hardware.

You will work closely with controls and robotics engineers to integrate learned policies into the robot control stack, ensuring stable and robust behavior in real-world conditions.

Development will involve continuous iteration between large-scale simulation and hardware experiments.

The problems you will work on include dynamic locomotion, balance recovery, contact-rich manipulation, and multi-behavior policy learning.

What You’ll Do

• Design and train reinforcement learning policies for humanoid robot control.

• Build scalable simulation and training pipelines (e.g., Isaac Lab, MuJoCo).

• Design reward functions, observation spaces, and curricula for complex behaviors.

• Improve robustness and sim-to-real transfer of learned policies.

• Deploy and evaluate policies on real robotic systems.

• Integrate policies into the control stack.

What We’re Looking For

• MS or PhD in Robotics, Machine Learning, Computer Science, or related field.

• Strong experience with reinforcement learning (e.g., PPO, SAC, offline RL).

• Experience applying RL to robotics or physical systems.

• Experience deploying learned policies on real robotic systems.

• Experience with physics-based simulation environments (e.g., Isaac Lab, MuJoCo).

• Strong programming skills in Python and/or C++.

Nice to have:

• Experience with RL for locomotion or legged robots.

• Experience with sim-to-real transfer.

• Familiarity with robot dynamics, control, or whole-body control.

What We Offer

• Meaningful time off to rest and recharge: 23 days of annual leave (accrued), 15 days of paid sick leave, and paid company holidays.

• Fully funded private healthcare for UK employees, with broad provider access, virtual and in‑person care, and strong mental health and serious illness support.

• Equity included–we believe builders should share in what they build.

• Pension scheme with a total 8% contribution (5% employee, 3% employer) on full earnings.

• Free daily breakfast, catered lunch, and snacks in‑office.

• Collaboration with top‑tier engineers, researchers, and product experts in AI and robotics.

• Freedom to influence the product and own key initiatives.