niantic-spatial - 3D Computer Vision Research Engineer - World Map
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 closely related area. • Demonstrated experience with 3D geometry and several relevant areas — multi-view reconstruction, SfM, SLAM, camera pose estimation, point-cloud registration, image-based localization, georeferencing, or sensor fusion. • The ability to formulate ambiguous real-world problems, choose the right mathematical or learning-based tools, and evaluate solutions rigorously. • Strong Python skills and experience with modern ML and scientific-computing libraries (PyTorch, NumPy, SciPy). • Strong software engineering skills — you can turn research prototypes into reliable, scalable, and maintainable systems. • A track record of taking an algorithm from research idea and experimental prototype through evaluation, benchmarking, and deployment on real-world data. • Clear written and verbal communication; able to collaborate effectively across research and engineering disciplines. • PhD in computer vision, robotics, machine learning, photogrammetry, geodesy, remote sensing, or a related field — not required, but valued. • A strong publication record or active involvement in the research community at venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, SIGGRAPH, 3DV, ICRA, or RSS. • Experience with learning-based approaches for visual or 3D understanding — transformers, point transformers, foundation models, or methods combining learned representations with explicit geometric priors. • Experience with aerial or satellite imagery, GNSS/GPS, geodesy, mapping systems, or large-scale spatial data. • Evidence of technical leadership, mentorship, or successful cross-functional delivery. • EQUAL OPPORTUNITY
Responsibilities
• Geospatial Registration — Develop and advance algorithms for world-scale georeferencing and registration across imagery, 3D reconstructions, point clouds, and geographic reference data. • 3D Geometry & Correspondence — Build and improve methods spanning multi-view geometry, SfM, SLAM, feature matching, learned correspondence, bundle adjustment, point-cloud registration, and ICP. • Data & Evaluation — Create the data and evaluation flywheel for world-scale mapping — design and maintain large-scale datasets, pipelines, benchmarks, and evaluation methodologies that expose hard failure modes, accelerate research iteration, and support production. • Learning-Based 3D Reasoning — Explore and develop learning-based approaches for geospatial understanding, combining transformers and 3D foundation models with geometric priors and uncertainty modeling. • Production Robustness — Design robust solutions for challenging real-world conditions: sparse or noisy GPS, changing appearance, inconsistent reconstruction quality, large geographic extents, and imperfect reference maps. • Cross-Functional Collaboration — Partner with leading researchers in visual localization, 3D computer vision, and mapping — as well as engineering and product teams — to identify high-impact problems and turn research breakthroughs into end-to-end production systems. • Research Communication — Share results clearly through technical writing, design reviews, and internal presentations; contribute to publications and open research where appropriate.
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. We welcome applications from candidates who require visa sponsorship. • INCLUSIVE APPLICATION
Apply in one click
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT