3D Computer Vision Research Engineer - World Map
Core
Build the geometric foundation of a next-generation world map by harmonizing heterogeneous data sources (phones, aerial imagery, LiDAR, 360 cameras) into accurate, AI-readable representations of real places.
Role type
Senior Research Engineer (3D Computer Vision & Geospatial Alignment)
Builds
A living, measured record of the real world for robots and machines to reason, learn, and act safely.
Domain
Geospatial AI, 3D Computer Vision, Robotics, Photogrammetry
Deliverable
production ML models
Required skills
3D computer vision, machine learning, robotics, photogrammetry, multi-view reconstruction, SfM, SLAM, camera pose estimation, point-cloud registration, georeferencing, sensor fusion, Python, PyTorch, NumPy, SciPy, software engineering, algorithm deployment
Preferred skills
PhD in computer vision/robotics/ML, strong publication record (CVPR/ICCV/NeurIPS), learning-based 3D understanding (transformers/foundation models), aerial/satellite imagery experience, technical leadership
Technologies
PyTorch, NumPy, SciPy, LiDAR, 360 cameras, GNSS/GPS
Responsibilities
Develop algorithms for world-scale georeferencing and registration; build methods for multi-view geometry and correspondence; create large-scale datasets and evaluation pipelines; explore learning-based approaches for geospatial understanding; design robust solutions for real-world conditions; collaborate with research and engineering teams to productionize technologies; share results through technical writing and presentations
Seniority
Senior, hands-on IC with research leadership potential
