Staff Perception Engineer

Senior/Staff AI Perception Engineer (Team Lead)San Francisco Bay Area, CA · Full-timeAbout the companyOur client is a venture-backed robotics company building general-purpose mobile manipulator robots for industrial applications - supporting use cases across logistics, retail, and manufacturing environments. Their robots run on a proprietary physical-intelligence software stack designed to generalize across applications without reprogramming. The team is well-funded, growing fast, and has already shipped its robot into live customer sites.The roleWe're hiring a Senior/Staff AI Perception Engineer (Team Lead) to advance a production 3D AI perception stack for industrial robots - covering object localization, pose estimation, scene reconstruction, and deployment on robot compute within tight cycle-time constraints. This is a role for someone who has taken AI perception from prototype through production and real-world operation, and who's comfortable making pragmatic tradeoffs across accuracy, latency, compute, data, and delivery timelines.The role carries both technical and people leadership for the Perception Team - you'll own the perception roadmap, set technical direction, and grow the team, while staying hands-on in the codebase (roughly a 60/40 split between IC work and leadership).What you'll doAdvance perception capabilities end to end - from problem definition and prototyping through deployment, monitoring, and production improvement.Develop and improve 3D perception algorithms for object localization, pose estimation, scene reconstruction, and manipulation using RGB-D and other sensing modalities.Diagnose and correct production failures caused by difficult scenes, lighting changes, sensor noise, and gaps between training data and real customer environments.Strengthen production readiness through better data, evaluation, regression testing, and field-failure analysis.Collaborate across robotics teams to integrate perception into planning, manipulation, controls, and system software.Lead and grow the Perception Team - own the roadmap, run design reviews, hire, and mentor as the team scales.What you'll bringMS or PhD in Robotics, Computer Vision, Computer Science, or a related field.5+ years developing robotic perception systems, with direct responsibility for deploying perception software in production on physical robots.Experience leading a technical team - setting direction, mentoring, running design reviews, owning delivery.Strong Python/C++ for real-time perception pipelines, including sensor-data processing and model integration using ROS/ROS2.Strong foundation in 3D geometry, camera calibration, RGB-D or point-cloud processing, and 3D object localization/pose estimation.Hands-on experience building AI perception models (PyTorch or similar) and deploying under latency/compute constraints on robot hardware.Nice to haveMulti-sensor fusion and synchronization across cameras, LiDAR, encoders, or other robot sensors.Edge inference optimization (TensorRT, ONNX Runtime, CUDA, quantization).Experience with Isaac Sim, synthetic data, or sim-to-real workflows.Experience deploying perception systems in warehouse, logistics, or industrial environments.Compensation$180K–$280K base, depending on experience, plus equity and benefits.Interested candidates should reach out confidentially to discuss further - company details will be shared once mutual interest is established.