Machine Learning Engineer (Semantic Scene Understanding)
Core
Design and train machine learning algorithms for real-time semantic scene understanding from UAV aerial imagery to improve operator situational awareness in defense operations.
Role type
Senior IC machine learning engineer (aerial imagery/defense)
Builds
Real-time semantic segmentation, object detection, classification, and tactical feature extraction pipelines for UAVs
Domain
Defense / Autonomous Systems / Aerial Imagery
Deliverable
production ML models
Required skills
Machine Learning theory, Linear Algebra, 3D-Geometry algorithms, Python, PyTorch, C++, Inference optimization (TensorRT, ONNX Runtime, CUDA), Edge deployment, Semantic segmentation, Object detection, Classification
Preferred skills
Experience shipping CV/ML algorithms in production for edge/embedded systems, Experience with EO/IR imagery, PhD in relevant field
Technologies
PyTorch, C++, TensorRT, ONNX Runtime, CUDA
Responsibilities
Develop state-of-the-art ML algorithms for semantic segmentation, object detection, and classification tailored to aerial imagery; Build high-level tactical features such as real-time road vectorization and dynamic obstacle mapping; Architect pipelines to align semantic data from multiple moving UAVs into a Common Operational Picture; Optimize and deploy algorithms into tactical C2 platforms using quantization and hardware acceleration
Seniority
Senior, hands-on IC
