Apply

Ready to go for it?

AI Apply speeds things up—apply directly if you prefer.

FREE ACCESS
5,000–10,000 jobs/day
Scoutfield Logo

See all jobs on Scoutfield

Search thousands of fresh jobs every day.

Discover
  • Fresh listings
  • Fast filters
  • No subscription required
Create a free account and start exploring right away.
Niantic Spatial, Inc.

3D Reconstruction Research Scientist/Engineer

Niantic Spatial, Inc.

. Conduct original research in 3D computer vision, machine learning, and spatial AI .

Posted 10/16/2026full-timeLondon • United KingdomMid-LevelSeniorWebsite

Tech Stack

Tools & technologies
PythonPyTorchC++

About the role

Key responsibilities & impact
  • Conduct original research in 3D computer vision, machine learning, and spatial AI
  • Publish research at top-tier venues including CVPR, ICCV, ECCV, and SIGGRAPH
  • Design, implement, and evaluate algorithms for 3D reconstruction, neural scene representations, 3D Gaussian Splatting, SfM, meshing, geometric deep learning, feed-forward models, generative models, and spatial foundation models
  • Collaborate with research scientists and engineers to transition research into customer-facing products
  • Work with real capture conditions, hardware constraints, and customers on short turnarounds
  • Build and run large-scale experiments and benchmarking frameworks
  • Collaborate with researchers in computer vision, machine learning, graphics, and robotics
  • Implement and iterate on state-of-the-art methods for academic publishing and production deployment
  • Deliver working prototypes to enterprise customers

Requirements

What you’ll need
  • PhD in Computer Vision, Robotics, Machine Learning, Computer Science, Mathematics, Physics, or a closely related field, or equivalent demonstrated research experience in industry
  • Strong research track record in 3D computer vision, including reconstruction, depth estimation, novel view synthesis, SfM, SLAM, or closely related areas
  • Meaningful publication record at top-tier venues such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, or equivalent
  • Strong programming skills in Python
  • Hands-on experience with PyTorch
  • Evidence of carrying an idea from research into something real, such as a shipped feature, production pipeline, widely used open-source release, or similar
  • Independence to drive research projects from idea generation through experimentation, publication, and handoff
  • Nice to have: experience with COLMAP or similar classical reconstruction tooling
  • Nice to have: C++ or CUDA experience and understanding of performance and on-device constraints
  • Nice to have: experience with meshing, texturing, or integrating modern geometry or generative representations into native 3D
  • Ability to work in the London office three days per week
  • Authorization to work without restrictions in the country where the position is based

Benefits

Comp & perks
  • Annual bonus
  • Equity
  • Comprehensive benefits package
  • Hybrid work model with three days per week in the London office