AI/ML Computer Vision Engineer — YOLO Pipelines (Hybrid)

CACI; Ashburn (VA); Hybrid; USD 120,000 - 180,000; Full time

Job summary

CACI is seeking a Mid-Level AI/ML Computer Vision Engineer to join our BEAGLE Agile Solution Factory team supporting the CBP client in Northern Virginia. You will build and deploy custom YOLO-based object detection models to process FMV feeds, parsing roads, vehicles, people, and terrain features.

You will curate datasets, train models, and deploy high-performance inference pipelines while collaborating in an Agile environment with senior leads, video engineers, and developers.

Qualifications

• 3-5 years of software engineering or data science experience, with 2+ years building/training computer vision models.
• Proficiency in Python and core ML libraries (NumPy, Pandas, Scikit-Learn).
• Hands-on experience with PyTorch or TensorFlow for training neural networks.
• Experience implementing YOLO (YOLOv8/v9) for object detection, segmentation, or classification.
• Familiarity with OpenCV/FFmpeg for image/video processing.
• Data curation, formatting, and experience with annotation platforms (CVAT, LabelImg).
• Git version control and collaboration on shared codebases.

Responsibilities

• Train, fine-tune, and evaluate custom YOLO models on proprietary datasets.
• Process and format raw video into high-quality training data.
• Annotate and curate datasets; generate synthetic data where needed.
• Develop inference pipelines to output structured predictions (JSON/Protobuf).
• Generate performance reports, confusion matrices, and precision-recall curves.
• Collaborate in an Agile/Scrum environment to deliver production-ready code in sprints.

Skills

Python programming

YOLO object detection

PyTorch or TensorFlow

OpenCV/FFmpeg

Data annotation tools

Git

Model benchmarking (mAP/FPS)

Education

B.S. in Computer Science/Data Science/Software Engineering

Tools

CVAT

LabelImg

Docker

ONNX

TensorRT

YOLO framework

Job description

CACI is seeking a Mid-Level AI/ML Computer Vision Engineer to join our BEAGLE Agile Solution Factory team supporting the CBP client in Northern Virginia. You will build and deploy custom YOLO-based object detection models to process FMV feeds, parsing roads, vehicles, people, and terrain features.

You will curate datasets, train models, and deploy high-performance inference pipelines while collaborating in an Agile environment with senior leads, video engineers, and developers.