Key responsibilities:
- Train behaviour-cloning and reinforcement-learning policies for locomotion and manipulation.
- Own the training pipeline on the sovereign GB10 / GPU estate.
- Design reward, curriculum and domain randomisation schemes.
- Measure policy performance on hardware, not only on held-out data.
Requirements:
- RL and imitation learning in practice
- PyTorch
- distributed training
- robotics policies deployed to real hardware
- sceptical about simulation-only results.
Salary:
Salary on application
The Manchester factory comes online Q1 2027. Roles are recruited ahead of that date, with start dates agreed individually.
#J-18808-Ljbffr
