SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Niantic Spatial is building spatial AI models and services to help machines reason, learn, and act safely in the physical world. The company transforms camera imagery, video, sensor data, and archives into accurate, AI-readable representations of real places.
You'll join the World Map Research Engineering team (Geospatial Alignment) as a Research Engineer or Senior Research Engineer, working on the geometric foundation of a next-generation world map. This is an end-to-end applied research role spanning strong engineering and data-systems work to R&D in 3D deep learning, transformers, and foundation models. You'll develop new algorithms, produce research data and evaluation assets, and engineer resulting capabilities into production systems.
The World Map team works with heterogeneous data sources including phone and handheld device captures, aerial imagery, LiDAR, 360 cameras, and external geographic/elevation data. The central challenge is harmonizing these sources, quantifying uncertainty, and maintaining consistency as the map evolves.
Key responsibilities include:
- Developing algorithms for world-scale georeferencing and registration across imagery, 3D reconstructions, point clouds, and geographic reference data
- Building and improving methods spanning multi-view geometry, SfM, SLAM, feature matching, learned correspondence, bundle adjustment, point-cloud registration, and ICP
- Creating data and evaluation flywheels for world-scale mapping—designing large-scale datasets, pipelines, benchmarks, and evaluation methodologies
- Exploring learning-based approaches for geospatial understanding, combining transformers and 3D foundation models with geometric priors
- Designing robust solutions for challenging real-world conditions: sparse/noisy GPS, changing appearance, inconsistent reconstruction quality, large geographic extents, and imperfect reference maps
- Partnering with researchers in visual localization, 3D computer vision, and mapping, as well as engineering and product teams
- Communicating results through technical writing, design reviews, presentations, and publications
You'll work at the intersection of cutting-edge research and scalable engineering, taking approaches from prototype through evaluation, benchmarking, and deployment on real-world data.
Requirements:
- Bachelor's or Master's degree in Computer Science, Robotics, Machine Learning, Photogrammetry, or closely related field (or equivalent research/industry experience)
- Strong grounding in 3D computer vision, machine learning, robotics, photogrammetry, or 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
- Ability to formulate ambiguous real-world problems, choose appropriate 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—ability to turn research prototypes into reliable, scalable, maintainable systems
- Track record of taking algorithms from research idea through experimental prototype, evaluation, benchmarking, and deployment on real-world data
- Clear written and verbal communication; ability to collaborate effectively across research and engineering disciplines
Nice to have:
- PhD in computer vision, robotics, machine learning, photogrammetry, geodesy, remote sensing, or related field
- Strong publication record or active involvement in research community (CVPR, ICCV, ECCV, NeurIPS, ICLR, SIGGRAPH, 3DV, ICRA, 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/satellite imagery, GNSS/GPS, geodesy, mapping systems, or large-scale spatial data
- Evidence of technical leadership, mentorship, or successful cross-functional delivery
