Research Scientist - 3D Reconstruction (SfM & SLAM)
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 focused on 3D reconstruction. You will advance methods that recover accurate camera poses and geometry from real-world imagery, working with both classical multi-view geometry and state-of-the-art learned reconstructors. The work includes structure-from-motion, bundle adjustment, SLAM, or feed-forward reconstruction, with a focus on robustness, accuracy, and methods that hold up on diverse real-world data.
Responsibilities
Design camera pose estimators and 3D reconstructors.
Build robust SfM and camera tracking pipelines for a variety of input imaging sensors.
Develop bundle adjusters and nonlinear optimizers, including non-perspective camera formulations.
Integrate and extend SOTA feed-forward reconstructors (VGGT, DA3, Pi3)
Advance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.
Build evaluation metrics for pose accuracy and reconstruction quality, and drive improvements against public & internal benchmarks.
Scale reconstruction methods to large, diverse real-world datasets while keeping them reliable and efficient.
Collaborate with researchers to bring reconstruction advances into production systems.
Key Qualifications
PhD in computer vision with a research focus on 3D reconstruction; publications at top venues (CVPR, ICCV, ECCV, NeurIPS).
Deep understanding of multi-view geometry: camera models, epipolar geometry, triangulation, PnP, etc.
Strong familiarity with SOTA deep reconstructors (VGGT, DA3, Pi3) and related areas such as deep MVS, learned matching, and monocular depth estimation.
Hands-on experience with SfM/SLAM systems (COLMAP, ORB-SLAM) and nonlinear least-squares solvers (Ceres).
Experience shipping production-grade 3D reconstruction systems is a strong plus.
Strong Python and PyTorch skills.
Comfortable debugging failure cases on challenging real-world data.
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
<p>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.</p> <p>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
Software Engineer Internship (2027 Start)
Optiverus·London, Canada
<p data-renderer-start-pos="29"> </p> <p data-local-id="6618a4c09482" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 []">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"><u data-prosemirror-content-type="mark" data-prosemirror-mark-name="underline">projects</u></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
Software Engineer - Build Platform
Optiverus·London, Canada
<p>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
Graduate Software Engineer
Optiverus·London, Canada
<p> </p> <p data-renderer-start-pos="1" data-local-id="126eb7d5a283">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
Graduate Quantitative Researcher (2027 Start)
Optiverus·London, Canada
<p>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
Research Scientist - Robot Learning (VLA / WAM)
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
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
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
