Robotics Control Engineer - Reinforcement Learning

ZipRecruiter; London; On-site; GBP 70,000 - 100,000; Full time

Job summary

A pioneering robotics company is seeking a Senior Reinforcement Learning Control Engineer in London. The successful candidate will develop locomotion control algorithms for advanced humanoid robots. Ideal candidates will possess a Master's or PhD along with deep expertise in reinforcement learning and experience in deploying control systems.

Benefits

High competitive salary

23 working days of vacation per year

Flexible working hours

Opportunity to work on latest technologies

Dynamic and innovative work environment

Qualifications

• At least 3+ years in control systems for legged robots.
• Strong expertise in reinforcement learning applied to robotics.
• Experience with hardware-in-the-loop testing.

Responsibilities

• Design and implement RL-based control policies for locomotion tasks.
• Conduct rigorous testing in both simulated and real-world environments.
• Collaborate closely with software and perception teams.

Skills

Reinforcement Learning

Robotics

Control Systems

Simulation

Python

C++

Education

Master's or PhD in Robotics or related field

Tools

Mujoco

Isaac Sim

Job description

Job Description

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.

We’re seeking a highly skilled Senior Reinforcement Learning (RL) Control Engineer to develop locomotion and whole body control skills for our humanoid robots. You’ll be at the cutting edge of robotics, responsible for developing advanced control algorithms that balance precision, efficiency, and adaptability. This role focuses on designing robust controllers for walking, balancing while manipulating, fall recovery, and other advanced mobility tasks. We’re seeking candidates with deep expertise in reinforcement learning and a strong track record of deploying control systems on physical robots.

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.

Vision:

In a world where artificial intelligence opens up new horizons, our faith in its potential unveils a new outlook where, together, humans and machines build a new future filled with knowledge, inspiration, and incredible discoveries. The development of a functional humanoid robot underpins an era of abundance and well-being where poverty will disappear, and people will be able to choose what they want to do. We believe that providing a universal basic income will eventually be a true evolution of our civilization.

Solution:

As the demands on our built environment rise, labour shortages loom. With the world’s workforce increasingly moving away from undesirable tasks, the manufacturing, construction, and logistics industries critical to our daily lives are left exposed. By deploying our general-purpose humanoid robots in environments deemed hazardous or monotonous, we envision a future where human well-being is safeguarded while closing the gaps in critical global labour needs.

Key Responsibilities:

• Design and implement RL-based control policies for locomotion tasks, including walking, balancing while manipulating, squatting, stair climbing, fall recovery, and other dynamic maneuvers.
• Model and simulate complex dynamics, taking into account robot kinematics, actuator limitations, and environmental interactions to optimize performance.
• Conduct rigorous testing in both simulated and real-world environments to validate algorithms and ensure robustness across various conditions.
• Collaborate closely with software and perception teams to integrate control strategies into the full-stack robotic system.

Required Qualifications:

• Master’s or PhD in Robotics, Control Systems, Machine Learning, or a related field.
• At least 3+ years of experience in the design and implementation of control systems for legged robots, focusing on locomotion.
• Strong expertise in reinforcement learning applied to robotics
• Deep understanding of humanoid robot dynamics.
• Proven and strong experience with hardware-in-the-loop testing and deployment on physical legged robots.
• Strong hands-on experience with robot simulation platforms such as Mujoco, Isaac Sim or similar environments.
• Proficiency in Python and C++ for algorithm development, testing, and deployment.
• Experience in topics like model-free RL, imitation learning, or hybrid control systems that combine classic and modern methods.

Qualifications:

• Experience with sensor fusion for state estimation (IMUs, joint encoders, force/torque sensors).
• Understanding of actuators dynamics and modeling, and limitations.

Benefits

• High competitive salary.
• 23 working days of vacation per year.
• Flexible working hours.
• Opportunity to work on the latest technologies in AI, Robotics, Blockchain and others.
• Startup model, offering a dynamic and innovative work environment.