3D Computer Vision Research Engineer - World Map
Niantic Spatial9 hours ago
London, United KingdomSenior
Responsibilities
- Develop algorithms for world-scale georeferencing and registration across imagery, 3D reconstructions, point clouds, and geographic reference data.
- Build methods for multi-view geometry, SfM, SLAM, feature matching, learned correspondence, bundle adjustment, point-cloud registration, and ICP.
- Design and maintain large-scale mapping datasets, pipelines, benchmarks, and evaluation methodologies.
- Develop learning-based 3D reasoning approaches using transformers, 3D foundation models, geometric priors, and uncertainty modeling.
- Engineer robust solutions for sparse or noisy GPS, changing appearance, inconsistent reconstruction quality, large geographic extents, and imperfect reference maps.
- Take research algorithms from prototypes through evaluation, benchmarking, and deployment in production systems.
- Collaborate with researchers, engineering teams, and product teams, and communicate results through technical writing, design reviews, presentations, and publications.
Requirements
- Bachelor’s or master’s degree in computer science, robotics, machine learning, photogrammetry, or a closely related field, or equivalent research or industry experience.
- Strong grounding in 3D computer vision, machine learning, robotics, photogrammetry, or a related field.
- Demonstrated experience with 3D geometry and areas such as multi-view reconstruction, SfM, SLAM, camera pose estimation, point-cloud registration, image-based localization, georeferencing, or sensor fusion.
- Ability to formulate ambiguous real-world problems, select appropriate mathematical or learning-based tools, and evaluate solutions rigorously.
- Strong Python skills and experience with PyTorch, NumPy, and SciPy.
- Strong software engineering skills for creating reliable, scalable, and maintainable systems from research prototypes.
- Clear written and verbal communication and effective collaboration across research and engineering disciplines.
- PhD in computer vision, robotics, machine learning, photogrammetry, geodesy, remote sensing, or a related field is valued but not required.
- Publication record or active research-community involvement at venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, SIGGRAPH, 3DV, ICRA, or RSS is valued.
- Experience with transformers, point transformers, foundation models, aerial or satellite imagery, GNSS/GPS, geodesy, mapping systems, or large-scale spatial data is valued.
- Evidence of technical leadership, mentorship, or successful cross-functional delivery is valued.
Benefits
- Competitive market-rate base salary plus annual bonus, equity, and a comprehensive benefits package.
- London office-based role with three days per week in the office.
- Candidates requiring visa sponsorship are welcome to apply.
Categories
About Niantic Spatial
Niantic Spatial builds computer‑vision and spatial computing software that maps real‑world environments and localizes people and machines within them. The company offers a platform with APIs and SDKs for creating AI‑native digital twins, visual positioning, and spatial question‑answering, serving robotics, AR/VR, defense, and industrial operations. Privately held, it sells its technology to enterprises that need precise, geometrically accurate understanding of physical spaces beyond GPS or screen‑bound systems.