Staff Engineer, Perception (R5611)
At a glance
Senior Machine Learning Engineering role at Shield AI. London · internship.
Pay not stated Machine Learning Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build VIO, visual SLAM, localization and vision-navigation systems for aircraft flying without GNSS
- Fuse camera and IMU data with other onboard sensors to estimate aircraft state reliably
- Create geometric vision components for tracking features, estimating poses and locating the aircraft
- Connect navigation software to flight-control and autonomy systems, then test it in flight
- Port and tune C++ perception pipelines for real-time use on embedded Linux and video hardware
What you bring
- Substantial hands-on work developing perception or navigation systems for robotics
- Strong background in VIO, visual SLAM, vision navigation or localization where GNSS is unavailable
- You understand camera, IMU fusion, state estimation, sensor calibration and timing alignment
- You bring strong C++ skills, Linux experience and deployments on autonomous aircraft or other robots
Who this fits
This role suits a senior robotics engineer focused on perception, navigation and embedded deployment, rather than general AI or object detection. The position is listed in London as hybrid and as an internship.
From the employer
Shield AI’s mission is to protect service members and civilians with intelligent systems. We are seeking a Senior or Staff Robotics Perception Engineer to develop and deploy advanced perception and navigation capabilities for autonomous aircraft operating in complex and GNSS-denied environments.
This role requires deep expertise in visual-inertial odometry (VIO), visual SLAM, vision-based navigation, state estimation, and camera–IMU sensor fusion. You will take algorithms from early-stage prototypes through embedded implementation, field testing, and flight validation on operational autonomous platforms.
This is not a general AI/ML or object-detection role. We are looking for an engineer whose core expertise lies at the intersection of robotics perception, VIO/SLAM, state estimation, camera and inertial sensing, and real-time embedded deployment.
What you'll do:
- Design, develop, and deploy VIO, visual SLAM, visual localization, and vision-based navigation capabilities for autonomous aircraft.
- Develop robust state-estimation and sensor-fusion solutions using cameras, IMUs, and other onboard sensors.
- Build geometric computer-vision components, including feature tracking, optical flow, pose estimation, triangulation, and visual localization.
- Develop geo-localization and map-matching capabilities 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 platforms.
- Develop and maintain real-time camera and video-processing pipelines using technologies such as GStreamer and V4L2.
- Optimize workloads for NVIDIA Jetson, Orin, or comparable embedded-compute platforms, 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, including 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.
Preferred qualifications:
- Experience with NVIDIA Jetson, Orin, or similar embedded-compute platforms.
- Experience optimizing perception workloads using CUDA, TensorRT, or comparable acceleration technologies.
- 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 frameworks and libraries such as OpenVINS, VINS-Fusion, ORB-SLAM3, GTSAM, Ceres Solver, OpenCV, or Kalibr.
Our international teammates receive a comprehensive total rewards package aligned to your country office location. For full details on compensation and benefits, please consult your talent acquisition partner.