Research Scientist - Robot Learning (VLA / WAM)

SpaitialLondon, CanadaPosted 2h agoonsite

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.

We're seeking a Research Scientist to train the policies that turn a world model into a robot that acts. You will own vision-language-action (VLA) and world-action models (WAM) end to end, starting, including data, backbone, action representation, training runs, and the evaluation that tells us whether a policy is genuinely competent or merely lucky. A world model that understands geometry and physics still doesn't act on its own; the policy is what closes that gap. This is a senior, hands-on research role for someone who has already trained manipulation policies that worked, and who can say precisely why the ones that didn't failed.

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.

Key Qualifications

A PhD in robotics, machine learning, or computer vision with a robot learning focus, from the PhD alone or followed by industry experience.
Publications at top venues such as (CoRL, RSS, ICRA, IROS or CVPR, ICCV, ECCV, NeurIPS), open-source work, and/or deployed systems.
Deep experience with modern robot policy designs (VLA, WAM, diffusion), trained end to end rather than fine-tuned from a released checkpoint.
Strong imitation learning fundamentals, and familiarity with RL fine-tuning of pretrained policies.
Fluency with VLM backbones and how to adapt them for control.
Expert Python and PyTorch, with multi-node distributed training experience (FSDP or equivalent).

At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

Find Jobs in United Kingdom on Arbeitnow

Skills

Engineering

Similar roles

Software Engineer - Digital Assets
Optiverus·London, Canada
Optiver is looking for a Senior Digital Assets Software Engineer to join our Digital Assets Tech Team in London. In this role, you’ll build and evolve trading systems for cryptocurrency markets, working closely with traders and researchers to deliver solutions in a fast-moving and constantly changing environment. You’ll play a key role in building out our digital assets platform, helping…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Software Engineer Internship (2027 Start)
Optiverus·London, Canada
  As a Software Engineering Intern, you will work side-by-side with your mentor and teammates to build software for Optiver’s real-time trading environment. You will work on <a href="https://www.optiver.com/join-us/stories/real-projects-real-impact-amsterdam-summer-tech-internship/" data-prosemirror-content-type="mark" data-prosemirror-mark-name="link">projects</a> that further develop and optimize our systems, testing and shipping code with guidance from experienced engineers and seeing how your…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Software Engineer - Build Platform
Optiverus·London, Canada
At Optiver, the velocity of our software development is a critical part of our competitive advantage. Our ability to compete depends on how quickly new ideas can move from insight to production. The Developer Experience team is a strategic engineering function with a clear mandate: improve the development lifecycle across the company in ways that accelerate delivery and reduce our…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Graduate Software Engineer
Optiverus·London, Canada
  As a Graduate Software Engineer, your work is mission-critical at our firm. You will work on solutions that enable us to react to markets at lightning-fast speeds. Your work will be the magic behind the scenes, enabling our teams to make split-second decisions with precision and confidence. By working in an interdisciplinary manner and innovating and optimising…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Graduate Quantitative Researcher (2027 Start)
Optiverus·London, Canada
If you enjoy using mathematics and code to investigate difficult questions, you could make a direct contribution to Optiver’s success in global markets. As a Graduate Quantitative Researcher, you’ll work across the full research process, from framing the question and choosing the data to building, testing and deploying models. Machine Learning is central to the work, whether you’re extracting signals,…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Research Scientist - 3D Reconstruction (SfM & SLAM)
Spaitial·London, Canada
SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Business Operations Manager
Spaitial·London, Canada
SpAItial is pioneering Physically-grounded World Models, a new AI paradigm designed to generate and reason about the appearance and physics of real and imagined environments. We are moving beyond 2D pixels to build models that natively understand the geometry of our world, and redefining how industries from robotics and AR/VR to gaming and cinema create and interact with 3D environments.…
- On-site
- Full-time
- Express Entry — PR day one, no employer
2h ago
Postdoctoral Researcher in geospatial political data (SDC-32)
GESIS – Leibniz-Institut für Sozialwissenschaften·Köln, Germany
GESIS – Leibniz-Institute for the Social Sciences is an internationally active research institute, funded by federal and state governments and member of the Leibniz Association. Starting on January 1, 2027 our Department Survey Data Curation, Team Survey Data Augmentation, located in Cologne, is looking for a Postdoctoral Researcher in geospatial political data (Salary group 13 TV-L, working time 100 %,…
- On-site
- Temp
- Blue Card — tied; settle 21–33mo
4h ago