Staff Engineer, Perception (R5611)

The role

Design, build and deploy visual-inertial odometry, visual SLAM and vision-based navigation for autonomous aircraft that fly in GNSS-denied environments. Take algorithms from prototype through embedded implementation, field testing and flight validation.

What you will do

• Design, develop and deploy VIO, visual SLAM, visual localization and vision-based navigation for autonomous aircraft.
• Develop state-estimation and sensor-fusion solutions using cameras, IMUs and other onboard sensors.
• Build geometric computer-vision components: feature tracking, optical flow, pose estimation, triangulation and visual localization.
• Develop geo-localization and map-matching using satellite, aerial or orthophoto imagery.
• Integrate perception and navigation algorithms with flight-control and autonomy systems.
• Implement and optimize algorithms in C++ for real-time operation on embedded Linux.
• Develop and maintain real-time camera and video pipelines using GStreamer and V4L2.
• Optimize workloads for NVIDIA Jetson, Orin or comparable embedded compute, including CUDA and TensorRT where appropriate.

Required qualifications

• Significant hands-on experience developing robotics perception or navigation systems.
• Strong expertise in VIO, visual SLAM, vision-based navigation or GNSS-denied localization.
• Deep understanding of camera–IMU sensor fusion, state estimation, calibration and time synchronization.
• Strong knowledge of geometric computer vision: feature tracking, optical flow, pose estimation, triangulation and visual localization.
• Experience deploying perception or navigation capabilities on UAS/UAVs or other autonomous robotic platforms.
• Strong C++ development skills and experience working in Linux environments.

Nice to have

• Experience with NVIDIA Jetson, Orin or similar embedded compute platforms.
• Experience optimizing perception workloads using CUDA, TensorRT or comparable acceleration.
• Hands-on experience with GStreamer, V4L2, camera pipelines and real-time video processing.
• Experience deploying containerized software to embedded platforms using Docker.
• Experience with vision-based navigation, geo-localization or map matching using satellite, aerial or orthophoto imagery.
• Familiarity with OpenVINS, VINS-Fusion, ORB-SLAM3, GTSAM, Ceres Solver, OpenCV or Kalibr.

Benefits

• Comprehensive total rewards package aligned to your country office location; full details from your talent acquisition partner.

About the company

Shield AI is a venture-backed defense-tech company whose mission is to protect service members and civilians with intelligent systems. Its products include Hivemind autonomy software, V-BAT and X-BAT aircraft, and Aechelon simulation technologies.