Senior AI/ML Engineer (Computer Vision)

About the role

CACI is looking for a Senior AI/ML Computer Vision Engineer with Agile methodology experience to join its BEAGLE Agile Solution Factory team supporting the Customs and Border Protection (CBP) client in Northern Virginia. You will lead a newly formed 3-person pod that designs, trains and deploys custom YOLO models to detect and parse objects in live full-motion video feeds.

Key responsibilities

• Lead a 3-person AI/ML team, setting technical direction, sprint goals, code standards and model evaluation metrics.
• Design, modify and train custom YOLO architectures tailored to CBP's video feeds.
• Architect the pipeline that ingests, cleans and pre-processes production video into a secure training/sandbox environment.
• Define annotation and labeling guidelines, manage dataset curation and handle class imbalance, weather and low-contrast challenges.
• Optimize inference speed (FPS) and accuracy (mAP, precision, recall) with tools such as NVIDIA TensorRT, DeepStream and CUDA.
• Integrate the live computer vision inference pipeline with the broader application and act as the primary point of contact for the pod in an Agile/Scrum environment.

Required profile

• U.S. citizen able to pass a CBP background investigation (felony checks, drug use and misconduct checks).
• Bachelor's, Master's or Ph.D. in Computer Science, Data Science, Electrical Engineering or a related field with an AI/ML focus.
• 7+ years of related technical experience, including 4+ years developing and deploying Deep Learning/Computer Vision models, heavily focused on object detection.
• Local candidates must be available for a hybrid schedule in Ashburn, VA.

Required skills

• Deep learning frameworks (PyTorch preferred, TensorFlow) and OpenCV.
• YOLO family models (Ultralytics YOLOv8/v9/v10, custom backbones) and training from scratch, including anchor boxes, loss functions and hyperparameters.
• NVIDIA CUDA, cuDNN, TensorRT or ONNX; video streams (RTSP, HLS) and frame-by-frame processing.
• Python at expert level; data curation, active learning and annotation tools (CVAT, LabelStudio, Roboflow).
• Desired: multi-object tracking (DeepSORT, ByteTrack), AWS SageMaker, edge deployment (Jetson) and CBP dataset experience.

What we offer

• Proposed pay range of $103,800 - $218,100.
• Healthcare, wellness, financial, retirement, family support, continuing education and time-off benefits.
• Flexible time off and learning resources.