AI/ML Engineer

CDIT • Ashburn, VA

3d • Hybrid

About The Position

CDIT is seeking a Mid-Level AI/ML Computer Vision Engineer to support the BEAGLE Agile Solution Factory (ASF) team serving U.S. Customs and Border Protection (CBP) in Northern Virginia. The role is part of a three-person computer vision pod building custom object detection and classification models with the YOLO framework. The team processes live and recorded Full-Motion Video (FMV) feeds to identify roads, vehicles, people, and terrain features.

This hands-on position involves bringing raw production video into a secure training environment, curating datasets, training and tuning models, and deploying high-performance inference pipelines. The engineer collaborates with the Senior AI/ML Lead, video engineers, and developers in an Agile/Scrum environment to deliver production-ready code in short sprints. The position requires working on site two to three days per week in Ashburn, Virginia, U.S. citizenship, and the ability to pass a CBP background investigation.

Requirements

• Bachelor of Science in Computer Science, Data Science, Software Engineering, or a related discipline.
• At least 5 years of software engineering or data science experience, including at least 2 years of hands-on experience building and training computer vision models.
• Python programming experience with core machine-learning libraries, including NumPy, Pandas, and Scikit-Learn.
• Hands-on experience training neural networks with PyTorch or TensorFlow.
• Experience implementing YOLO, such as YOLOv8 or YOLOv9, for object detection, segmentation, or classification.
• Image and video processing experience with OpenCV or FFmpeg.
• Data curation and formatting experience, including use of annotation platforms such as CVAT or LabelImg.
• Git version control and experience collaborating on shared codebases.
• Strong analytical skills focused on benchmarking model performance, including mAP, FPS, and inference latency.
• Willingness to work on site 2–3 days per week in Ashburn, Virginia.
• U.S. citizenship and ability to pass a CBP background investigation, including checks for felony convictions over the previous 3 years and illegal drug use or misconduct such as theft or fraud over the previous year.

Nice To Haves

• Experience with containerized development environments such as Docker.
• Experience with GPU execution environments and model export formats such as ONNX and TensorRT.
• Experience with multi-object tracking libraries.
• Experience with Agile tools such as Jira and Confluence.

Responsibilities

• Train, fine-tune, and evaluate custom YOLO object detection models on proprietary datasets; experiment with hyperparameters, augmentations, and model sizes to balance speed and accuracy.
• Process, clean, and format raw video recorded in production environments into high-quality training datasets.
• Manage the annotation lifecycle, including labeling images and video frames, verifying annotation quality, and generating synthetic data when needed.
• Write Python scripts to parse video frames, feed them into inference engines, and export structured prediction data in JSON or Protobuf for detected objects.
• Produce performance reports, confusion matrices, and precision-recall curves to identify model blind spots and drive continuous improvement.
• Partner with the Senior AI/ML Lead, video engineers, and developers in an Agile/Scrum environment to deliver production-ready code in short sprints.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level