Spaitial
Research Scientist - Robot Learning
Salary not disclosedOnsite
- Engineering
- London
- Full time
- Yesterday
Newly posted
About the role
SpAItial is seeking a Research Scientist to train policies that enable world models to control robots. You will own the end-to-end development of vision-language-action (VLA) and world-action models (WAM), including data curation, model architecture, training, and evaluation. This is a hands-on role focused on bridging the gap between world models and physical robot action.
Responsibilities
- Own the training pipeline for vision-language-action (VLA) and world-action models (WAM) end to end, from data to a policy running on a robot.
- Contribute to setting the technical direction for embodied research at SpAItial.
- Close the sim-to-real gap through domain randomization, system identification, and calibration, and build evaluation that predicts real-world transfer.
- Adapt VLM backbones for control: encoder choice and adapter strategies, co-training.
- Curate and weight the training mix across heterogeneous robot datasets, spanning differing embodiments, action spaces, and sensor setups.
- Design action representation and decoding, including tokenization, chunking, diffusion, and flow-matching action experts.
- Build the world-model components that predict future observations conditioned on action.
- Run post-training: supervised fine-tuning onto target embodiments, and RL for robustness beyond demonstrations.
Required skills
- Robot learning
- VLA
- WAM
- Imitation learning
- Reinforcement learning
- VLM backbones
- Python
- PyTorch
- Distributed training
- FSDP
Qualifications
- PhD in robotics, machine learning, or computer vision with a robot learning focus
- Publications at top venues such as CoRL, RSS, ICRA, IROS, CVPR, ICCV, ECCV, or NeurIPS
- Experience with open-source work or deployed systems
About the Company
SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. They are redefining how industries generate and interact with physically-grounded 3D environments.