3D Reconstruction Research Scientist/Engineer

Niantic Spatial, Inc.; Greater London; Sur place; GBP 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

Annual bonus

Equity

Comprehensive benefits

Résumé du poste

Niantic Spatial, Inc. in London seeks a 3D Reconstruction Research Scientist/Engineer to push the frontier of spatial AI, from academic discovery to customer-ready technology.

You will work with experts in CV, ML, graphics, and robotics on large-scale spatial understanding, localization, and geospatial models. You’ll contribute to research-to-production workflows, delivering prototypes for enterprise customers while maintaining a strong publication track record and collaboration across

Qualifications

• PhD in Computer Vision, Robotics, ML, CS, Math, Physics, or equivalent research experience.
• Strong 3D CV research track record: reconstruction, depth estimation, novel view synthesis, SLAM.
• Meaningful publication record at top venues (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS).
• Strong Python programming skills and PyTorch experience.
• Ability to translate research into production: shipped feature, pipeline, or open-source release.

Responsabilités

• Research & Publication – Conduct original research in 3D computer vision, ML, and spatial AI; publish at top-tier venues.
• Algorithm Development – Design and evaluate 3D reconstruction, neural scene representations, SfM, meshing, and spatial models.
• Research-to-Production – Collaborate to translate ideas into customer-facing products in real capture conditions.
• Large-Scale Experimentation – Build and run large-scale experiments and benchmarking frameworks.
• Cross-Disciplinary Collaboration – Partner with CV, ML, graphics, robotics researchers for scale.
• Rapid Prototyping – Implement and iterate state-of-the-art methods for publishing and production.

Connaissances

3D computer vision

Python

PyTorch

Publications

Independent researcher

Formation

PhD in Computer Vision/ML

Outils

COLMAP

C++/CUDA

Description du poste

About Niantic Spatial

AI has learned from almost everything online, but it still struggles with the physical world, where 99.5% of economic activity happens. It doesn't know where things are, how spaces fit together, or what changes over time.

That's one of the biggest unsolved problems in AI, and it's the one we're solving at Niantic Spatial. We build spatial AI models and services so people and machines can reason, learn and act safely in the physical world. We turn camera imagery, video, sensor data and archives into accurate, AI-readable representations of real places that robots can train in and machines can use to know exactly where they are.

In physical AI, mistakes have real consequences. That's why we build AI grounded in measured reality, not guesswork, so the people and machines relying on it can trust it to get things right.

Our team built some of the world's most widely used maps. Now we're building something bigger: a living, measured record of the real world that machines can query, learn from and use to understand how places change over time. If you want to help AI understand the world we actually live in, come build with us.

About the Role

You’ll join our Research Team in London as a 3D Reconstruction Research Scientist/Engineer – working at both ends of the pipeline, from cutting-edge academic research to shipping directly to customers. Our team builds the reconstruction technology that turns casually captured or domain-specific imagery into high-fidelity 3D reconstructions: everything from Structure-from-Motion through 3D Gaussian Splatting, feed-forward models, and generative models. We've shipped 360 splatting to consumers and enterprise customers, developed the splatting tech that runs on phones, and published at CVPR, ICCV, ECCV, and SIGGRAPH - more often than not, our papers end up in production.

You’ll work alongside world-class researchers in computer vision, machine learning, graphics, and robotics on large-scale spatial understanding, localization, reconstruction, scene understanding, and geospatial foundation models. This role is open to junior and senior researchers; scope and responsibility are calibrated to your experience.

What You’ll Do

• Research & Publication – Conduct original research in 3D computer vision, machine learning, and spatial AI; publish findings at top-tier venues including CVPR, ICCV, ECCV, and SIGGRAPH.
• Algorithm Development – Design, implement, and evaluate novel algorithms across 3D reconstruction, neural scene representations, 3D Gaussian Splatting, SfM, meshing, geometric deep learning, feed-forward models, generative models, and spatial foundation models.
• Research-to-Production – Collaborate with research scientists and engineers to transition promising ideas into customer-facing products – working directly with real capture conditions, real hardware constraints, and real customers on short turnarounds.
• Large-Scale Experimentation – Build and run large-scale experiments and benchmarking frameworks to rigorously validate and advance new methods.
• Cross-Disciplinary Collaboration – Partner with world-class researchers in CV, ML, graphics, and robotics to advance large-scale spatial understanding, localization, reconstruction, and geospatial foundation models.
• Rapid Prototyping – Implement and iterate on state-of-the-art methods for both academic publishing and production deployment, delivering working prototypes to enterprise customers with speed and quality.

What You’ll Bring

• PhD in Computer Vision, Robotics, Machine Learning, Computer Science, Mathematics, Physics, or a closely related field – or equivalent demonstrated research experience in industry.
• A strong research track record in 3D computer vision: reconstruction, depth estimation, novel view synthesis, SfM, SLAM, or closely related areas.
• A meaningful publication record at top-tier venues (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, or equivalent).
• Strong programming skills in Python and hands-on experience with PyTorch.
• Evidence that you can carry an idea from research into something real – a shipped feature, a production pipeline, a widely used open-source release, or similar.
• The independence to drive research projects from idea generation through experimentation, publication, and handoff.

Nice to Have

• Experience with classical reconstruction tooling (COLMAP or similar).
• C++ or CUDA experience, and a feel for performance and on-device constraints.
• Experience with traditional 3D techniques – meshing, texturing, or bringing modern geometry or generative representations into native 3D.

Compensation & Benefits

• Base salary: Competitive market rate. Compensation also includes an annual bonus, equity, and a comprehensive benefits package.

Location & Work Model

• This role is based in our London office, with three days per week in office.

Inclusive Application

We know the strongest candidates don't always tick every box. If you're excited about this role and believe you could do it well, we