We’re building a new generation of autonomous ISR aircraft capable of sensing, deciding, and acting in milliseconds - without relying on the cloud.
You’ll lead the perception stack that powers onboard visual intelligence. Your work will enable aircraft to detect, track, and understand the world in real time.
What you’ll do
- Build and deploy high-performance visual detection, tracking, and classification systems for real-time flight.
- Integrate perception models with onboard agents (Intel, Pilot, Operator) to drive coordinated autonomy.
- Optimize CNN and transformer-based models for embedded inference (Jetson, Hailo, or equivalent).
- Develop pipelines for training, testing, and validating vision models using aerial and ground datasets.
- Implement real-time sensor fusion across video, IMU, GPS, and telemetry data streams.
- Contribute to continuous improvement of data collection, labeling, and active-learning loops.
What we're looking for
- Strong background in computer vision, deep learning, and image/video processing.
- Experience with modern vision architectures (YOLOv5/v8, DETR, RT-DETR, or similar).
- Proficiency in Python and PyTorch; familiarity with TensorRT, OpenVINO, or ONNX runtimes.
- Experience deploying optimized models on embedded hardware (NVIDIA Jetson, Hailo, etc.).
- Understanding of multi-sensor fusion and real-time inference under constrained resources.
Nice to have
- Experience building flight-ready or edge-deployed perception systems.
- Familiarity with PX4/ArduPilot/MAVLink or other UAV telemetry systems.
- Background in optical flow, 3D reconstruction, or SLAM.
- Comfort working with aerial datasets, synthetic data generation, or 3D simulation (Three.js, Unreal, Cesium).
- Knowledge of model compression, quantization, and real-time video encoding/streaming.
Why USAVX
USAvionix builds autonomous systems that act faster and smarter than the threat. In this role, you’ll own one of our core technologies - shaping how autonomy is coordinated, deployed, and trusted in the field.