Computer Vision Engineer
BrightAI Corporation3 hours ago
Palo Alto, CA, USAMid Level
Responsibilities
- Build Gaussian-splatting and photogrammetric reconstruction pipelines for metrically accurate, georeferenced drone scenes.
- Develop pose and state-estimation systems using bundle adjustment, RTK/GNSS and IMU fusion, visual-inertial odometry, and multi-camera calibration.
- Convert reconstructions into training and evaluation environments for flight policies and analyze sim-to-real divergence.
- Develop change-detection capabilities across reconstructions captured weeks or months apart.
- Define perception outputs and degradation behavior for autonomy planning, including latency and failure modes.
- Train and deploy detection and auto-labeling models on aircraft within real latency and power budgets.
- Work with real aircraft and customer sites to diagnose failures and move prototypes into field trials.
Requirements
- At least 2 years of computer vision or robotics-perception experience with systems deployed outside a laboratory.
- Strong understanding of multi-view geometry and practical ability to debug bundle-adjustment failures.
- Hands-on experience with SLAM, SfM, or visual-inertial odometry.
- Strong PyTorch skills and experience training and debugging models on real-world field data.
- Experience working on a moving platform such as a drone, vehicle, or robot.
- Comfort with camera synchronization, calibration rigs, and flight-log analysis.
- Sufficient robotics knowledge to collaborate with autonomy teams on planner requirements, latency, and perception failure modes.
- Strong written communication skills for producing actionable design documents.
- Experience with 3DGS or NeRF, especially for large outdoor scenes, reconstruction-backed robot-training simulation, sim-to-real transfer, learned dynamics, ROS/ROS2, PX4/ArduPilot, C++ alongside Python, or thermal, depth, or lidar fusion is preferred.
Benefits
- Palo Alto hybrid work arrangement.
- Small team with high autonomy and a short path from prototype to field trial.
- Direct access to real aircraft and customer sites.
Categories
ML EngineeringRobotics
About BrightAI Corporation
BrightAI is transforming essential services with Physical AI—real-world intelligence that drives proactive, data-driven operations. Built on the Stateful platform, BrightAI empowers operators of critical infrastructure to collect and connect sensor data in real time, uncover hidden insights, and make smarter decisions. From predictive diagnostics and autonomous robotics to digital twins and AI-enabled workflows, BrightAI solutions serve industries including water, power, gas compression, pest control, HVAC, and manufacturing. By turning complex physical signals into actionable intelligence, BrightAI is redefining how essential services are delivered and sustained.