Computer Vision Engineer (PhD) — 3D Perception & Multi-View Geometry

STEALTH ROBOTICS STARTUP — HIRINGComputer Vision Engineer (PhD) — 3D Perception & Multi-View GeometryRemote · Part-time to start (10-20 hours/week), scaling to full-time as we growCompensation: $2500-5,000 / month + 1-4% equityABOUT USWe're a stealth robotics startup building real-time spatial intelligence for physical operations — turning multi-camera and on-robot sensor streams into a live, queryable 3D scene graph of a space, running on NVIDIA edge compute (Jetson-class) with TensorRT foundation models. Small, exceptional, AI-augmented team, targeting a first deployment in 2026. Full product and architecture shared under NDA once we're talking.You'll work on real sensor data and its messiness — calibration drift, depth noise, motion blur, multi-view ambiguity — and ship code that runs in production on the edge, not just in a notebook.Critical requirement: you ship production-grade, tested code that runs in real time on real sensor data at the edge — not research notebooks. If it isn't reproducible and benchmarked on target hardware, it isn't done.THE ROLE — THE WORLD FRAME EVERYTHING RESTS ONYou own the metric foundation the rest of the perception stack is built on: getting many uninstrumented cameras and on-robot sensors into precise, drift-free agreement, and fusing them into a consistent 3D map.Focus: multi-camera and cam-to-IMU calibration (AprilGrid intrinsics, inter-cam extrinsics, time-offset estimation), VIO/SLAM, and volumetric (TSDF/ESDF) fusion into a consistent metric map.WHAT YOU'LL DO• Design, implement, and productionize perception components that run in real time on edge hardware.• Own the path from research idea to tested, benchmarked, deployed module (we take testing and reproducibility seriously).• Work across the boundary with robotics, ML-deployment, and platform — integration is where the hard problems live.• Validate on real rigs (fixed multi-camera rigs + on-robot depth/IMU) and close the loop on real-world failure modes.MUST HAVE• Deep multi-view geometry (calibration, bundle adjustment, SE(3)).• Hands-on SLAM/VIO (VINS/OKVIS/ORB-SLAM class) and/or volumetric fusion (TSDF-class).• Solid grasp of sensor models and uncertainty.BASELINE REQUIREMENTS• PhD in Computer Vision, Robotics, or ML — or equivalent depth via a strong record of shipped, real-world CV systems.• Fresh PhDs welcome. Non-PhD candidates need an equivalent record of deployed systems. We calibrate level (early-career to senior) to the person, not to a year count.• Demonstrated experience: first-author publications or shipped systems; has owned a component end-to-end.• Expert Python; strong C++ or Rust; genuine software-engineering discipline (tests, code review, real repos — not throwaway scripts).• Fluency with real sensor data and comfort debugging the physical-world edge cases synthetic data never shows.Level: early-career to senior.KEY DELIVERABLES• A reproducible multi-cam + cam-to-IMU calibration pipeline (validated extrinsics + recovered time-offset, with tests).• A fused TSDF/ESDF map built from real rig data.• A calibration/fusion accuracy + latency report on target hardware.BONUSKalibr, factor graphs (GTSAM/Ceres), depth-sensor calibration, ESDF/planning substrates.STACKPython · Rust (client) · C++ (perf paths) · PyTorch · TensorRT / ONNX (BF16) · OpenCV · ROS 2 / DDS · GPU volumetric fusion · NVIDIA Jetson-class edge compute · stereo/depth cameras · AprilTag/Kalibr.We optimize for exceptional cross-disciplinary engineers over headcount — if you also span foundation-model edge deployment or scene-graph reasoning deeply, tell us.How to apply: email jaribido@imasiv.ai with your CV and a short note. Referrals welcome.