Senior Reinforcement Learning Engineer

ReeVR Talent; Greater London; On-site; GBP 90,000 - 140,000; Full time

Job summary

ReeVR Talent in London is seeking a Senior Reinforcement Learning Engineer to advance dynamic locomotion, balance, and manipulation in cutting-edge robotics. You will take policies from simulation to real hardware, owning the RL pipeline end-to-end.

The role emphasizes hands-on RL, Python and/or C++ programming, and experience with physics-based simulators like MuJoCo and Isaac Lab, with senior-level ownership and collaboration with controls engineers.

Qualifications

• Strong hands-on experience with reinforcement learning, including PPO, SAC or offline RL.
• Experience applying RL to robotics or physical systems.
• Experience deploying learned policies on real robotic hardware.
• Strong Python and/or C++ programming skills.
• Experience with physics-based simulation environments.

Responsibilities

• Design and train RL policies for robotic control.
• Build scalable training pipelines using MuJoCo or Isaac Lab.
• Design reward functions, observations and training curricula.
• Improve sim-to-real transfer and policy robustness.
• Deploy and evaluate policies on real robotic systems.
• Collaborate with controls and robotics engineers to integrate policies.

Skills

Reinforcement learning

PPO

SAC

Offline RL

Python

C++

MuJoCo

Isaac Lab

Simulation environments

Robotics

Tools

MuJoCo

Isaac Lab

Job description

Senior Reinforcement Learning Engineer - Robotics | London

We're working with a highly innovative robotics company developing next-generation robotic systems, and we're looking for a Senior Reinforcement Learning Engineer to join the team.

You'll work on challenging problems across dynamic locomotion, balance, contact-rich manipulation and multi-behaviour learning, taking policies from large-scale simulation through to deployment on real hardware.

What you'll do

• Design and train RL policies for robotic control
• Build scalable training pipelines using Isaac Lab, MuJoCo or similar
• Design reward functions, observations and training curricula
• Improve sim-to-real transfer and policy robustness
• Deploy and evaluate policies on real robotic systems
• Work closely with controls and robotics engineers to integrate learned policies

What we're looking for

• Strong hands-on experience with reinforcement learning, such as PPO, SAC or offline RL
• Experience applying RL to robotics or physical systems
• Experience deploying learned policies on real robotic hardware
• Strong Python and/or C++
• Experience with physics-based simulation environments

Experience with locomotion, sim-to-real, robot dynamics, control or whole-body control is particularly relevant.

This is a highly technical, senior-level opportunity with significant ownership across the RL pipeline, from simulation and training through to real-world deployment.

Location: London

Level: Senior

For further details, please get in touch for a confidential conversation.