Computer Vision Engineer
Core
Build custom object detection and classification models using the YOLO framework to process live and recorded Full-Motion Video (FMV) feeds for automated parsing of entities like roads, vehicles, people, and terrain features.
Role type
Mid-Level AI/ML Computer Vision Engineer
Builds
Production-ready object detection models and inference pipelines for federal clients
Domain
Computer Vision / Video Analytics / Federal Government
Deliverable
production ML models
Required skills
Python, PyTorch, TensorFlow, YOLO (v8/v9), OpenCV, FFmpeg, Data Annotation, Git, Model Evaluation (mAP, FPS)
Preferred skills
Docker, ONNX, TensorRT, Multi-object tracking, Jira, Confluence
Responsibilities
Train and fine-tune YOLO object-detection models; Process and curate raw video datasets; Write Python scripts for inference pipeline development; Generate performance reports and confusion matrices; Collaborate in Agile/Scrum sprints
Seniority
Mid-Level, hands-on IC