Senior Software Engineer, 3D Computer Vision

Field AI is seeking a passionate Senior Software Engineer, 3D Computer Vision to play a vital role in the development of advanced algorithms for 3D reconstruction and spatial understanding. In this role, you will work with data from high-fidelity laser scanners and imaging sensors to design and optimize workflows for processing, analyzing, and structuring 3D point cloud datasets. The ideal candidate will have deep expertise in computational geometry and point cloud processing algorithms, delivering high-quality, maintainable code without necessarily requiring a background in robot hardware. Your contribution is essential to helping us extract precise geometric truths from the real world to ensure our continued growth and value.

What You Get To Do

• Develop and optimize point cloud processing pipelines, including registration, denoising, normal estimation, segmentation, and primitive extraction
• Design efficient algorithms for large-scale, unstructured 3D datasets with attention to memory and runtime performance
• Implement production-grade computational geometry and linear algebra in C++ and Python
• Solve complex reconstruction challenges such as loop closure, global consistency, and multi-view fusion
• Evaluate and integrate emerging 3D vision methods (e.g., neural implicit representations, advanced meshing techniques)
• Partner with platform teams to ensure scalable, efficient deployment of algorithms

What You Bring

• 4+ years of experience in Computer Vision, Computational Geometry, or 3D-focused Software Engineering
• Master’s or Ph.D. in Computer Science, Applied Mathematics, or related field with specialization in 3D vision or geometric processing
• Strong proficiency in modern C++ (C++14/17) and Python
• Solid mathematical foundation in 3D geometry, linear algebra, rigid body transformations (SE(3), quaternions), and projective geometry
• Deep experience with point cloud algorithms (ICP, GICP, RANSAC, NDT, region growing) and spatial data structures (k-d trees, octrees, voxel grids)
• Hands-on experience with libraries such as PCL, Open3D, Eigen, or Ceres
• Familiarity with common 3D data formats (PCD, PLY, E57, LAS)
• Strong problem-solving skills and ability to translate academic research into production-ready code

What Sets You Apart

• Experience with non-linear optimization frameworks (Ceres, GTSAM, g2o) for bundle adjustment or pose graph optimization
• Background in SLAM or Structure from Motion (SfM) pipelines
• Experience processing LiDAR, RGB-D, or photogrammetry datasets
• Familiarity with Linux development environments and containerization (Docker)
• Exposure to ROS (not required)
• Knowledge of survey-grade accuracy standards and georeferencing algorithms