Reinforcement Learning Engineer - Manipulation

📋 Description

• Train language-vision conditioned manipulation policies via RL in simulation and real world.
• Construct diverse manipulation task suites in simulation.
• Partner with teleoperations to collect trajectories for behavior cloning.
• Partner with testing and operations to establish real-world RL pipelines.
• Experiment with sim-to-real transfer of policies.

🎯 Requirements

• 3+ years building deep-learning systems with shipped models or artifacts.
• Hands-on with LLMs, VLMs, or image/video generative models.
• Experience solving real problems using RL with deep neural networks.
• Strong Python + PyTorch/JAX; profiling numerics and maintainable code.
• Self-driven, proactive, good communicator; document experiments and trade-offs.

🎁 Benefits

• Competitive equity: stock options with upside as we scale.
• 30+ paid days off, including 23 days of annual leave and UK holidays.
• Private healthcare, including virtual and in-person care.
• Pension scheme with 8% total contribution (5% employee, 3% employer).
• Free daily breakfast, catered lunch, and snacks in-office.