Computer Vision Engineer — Perception for Autonomy Location: [Palo Alto / hybrid] The role: We fly drones that inspect real infrastructure. That means reconstructing sites accurately enough to detect change over time, and giving the autonomy stack a picture of the world it can actually act on. You'll own perception for a moving platform — reconstruction, pose, and the simulated environments we use to train and evaluate flight behavior. You'll work closely with the autonomy side without owning the flight controller. What you'll work on: <ul> <li>Reconstruction — Gaussian splatting and photogrammetric pipelines producing metrically accurate, georeferenced scenes from drone imagery</li> <li>Pose and state estimation — bundle adjustment, RTK/GNSS and IMU fusion, visual-inertial odometry, multi-camera calibration</li> <li>Simulation for autonomy — turning reconstructions into training and evaluation environments for flight policies, and characterizing where sim diverges from reality</li> <li>Change detection across reconstructions separated by weeks or months</li> <li>Perception in the loop — defining what reconstruction and detection deliver to planning, and what happens when the estimate degrades</li> <li>Detection and auto-labeling models running on the aircraft under real latency and power budgets</li> </ul> What we need: <ul> <li>2+ years in computer vision or robotics perception, with systems that ran outside a lab</li> <li>Solid multi-view geometry — you can reason about what your estimator is doing and debug a bundle adjustment that won't converge</li> <li>Hands-on SLAM, SfM, or visual-inertial odometry</li> <li>Strong PyTorch; real experience training and debugging models on field data that doesn't look like the benchmark</li> <li>Have worked on a moving platform — drone, vehicle, or robot — where ground truth is expensive and failures happen on site</li> <li>Comfortable at the hardware boundary: camera sync, calibration rigs, reading flight logs</li> <li>Enough robotics literacy to talk to the autonomy team — you know what a planner needs from perception and why latency and failure modes matter to it</li> <li>Writes clearly enough that another team can act on your design doc</li> </ul> Strong signals: <ul> <li>3DGS or NeRF, especially large outdoor scenes</li> <li>Reconstruction-backed simulation for robot training</li> <li>Sim-to-real transfer or learned dynamics</li> <li>ROS/ROS2, PX4/ArduPilot exposure</li> <li>C++ alongside Python</li> <li>Thermal, depth, or lidar fusion</li> </ul> How we work: Small team, high autonomy, short path from prototype to field trial. Direct access to real aircraft and real customer sites. We hire people who go find the failure themselves.

Computer Vision Engineer - Perception for Autonomy

Job Description