Job Description
📋 Description Lead research and development of perception systems for humanoid robots to enable robust autonomy Design and optimize deep learning models for real-time detection, tracking, segmentation, and scene Integrate multi-sensor data (Cameras, LiDAR, depth, IMUs) into unified world models to support Collaborate across RL, platform software, and systems teams; mentor junior engineers; shape Ensure latency, accuracy, and reliability requirements on edge devices through profiling, testing Define perception-to-action interfaces with planning and control teams for real-time compatibility. 🎯 Requirements MS/PhD in CS, Robotics, Computer Engineering, or related field. 3-5+ years building/deploying perception systems in robotics/real-time vision. Strong CV deep learning background: detection, segmentation, multi-object tracking, 3D perception. Hands-on with PyTorch, JAX, or TensorFlow; OpenCV, Detectron2, YOLO; foundation models for Python and modern C++; software engineering fundamentals (version control, testing, CI/CD). Deep understanding of 3D geometry, camera models, probabilistic estimation (EKF/UKF, SLAM, VIO). 🎁 Benefits Direct hire with opportunity to impact humanoid robotics at scale. Collaborative, human-centered work culture focusing on safety and real-world impact. Competitive compensation and equity in a fast-growing robotics company.
