Senior Software Engineer, 3D Computer Vision

Job description

Field AI is transforming how robots interact with the real world. We are building risk-aware, reliable, and field-ready AI systems that address the most complex challenges in robotics, unlocking the full potential of embodied intelligence. We go beyond typical data-driven approaches or pure transformer-based architectures, and are charting a new course, with already-globally-deployed solutions delivering real-world results and rapidly improving models through real-field applications. 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