> Markdown version of [/jobs/ext/4171751-3d-computer-vision-research-engineer-world-map](https://www.wearedevelopers.com/jobs/ext/4171751-3d-computer-vision-research-engineer-world-map). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# 3D Computer Vision Research Engineer - World Map

- **Company:** Niantic, Inc.
- **Location:** London, United Kingdom
- **Contract:** Permanent contract
- **Skills:** Computer Vision, Big Data, Global Positioning Systems (GPS), Python (Programming Language), Machine Learning, NumPy, Reference Data, SciPy, Sensor Fusion, Software Engineering, Spatial Data Infrastructures, Pytorch, Large Language Models, Deep Learning, Information Technology, Lidar, GNSS
- **Published:** October 19, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=2fb0ee50d38d4df7

## About the Role

* 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.

## Description

You'll help build the geometric foundation of the next-generation world map - joining our World Map Research Engineering team (Geospatial Alignment) as a Research Engineer or Senior Research Engineer. This is an end-to-end applied research role that spans from strong engineering and data-systems work to R&D in 3D deep learning, transformers, and foundation models. You'll develop new algorithms, produce the research data and evaluation assets needed to advance them, and engineer the resulting capabilities into dependable production systems.

The World Map team works with heterogeneous captures from phones and handheld devices, aerial imagery, LiDAR, and 360 cameras, as well as external geographic and elevation data. The central challenge is to harmonize these data sources, quantify uncertainty, and maintain consistency as the map evolves.

You'll work at the intersection of cutting-edge research and scalable engineering - developing new approaches to geospatial registration, correspondence, and geometric optimization, then productionizing these technologies to directly improve Niantic Spatial's world model.

What You'll Do

 * 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.