{"schemaVersion":"jobsearcher.job.v1","id":"ceee82358a86eca97ade68d1","url":"https://jobsearcher.com/jobs/ceee82358a86eca97ade68d1","canonicalUrl":"https://jobsearcher.com/jobs/ceee82358a86eca97ade68d1","title":"AI/ML Engineer (Computer Vision)","description":"Senior AI/ML Computer Vision EngineerCDIT is seeking a Senior AI/ML Computer Vision Engineer with Agile experience to join the BEAGLE (Border Enforcement Applications for Government Leading-Edge Information Technology) Agile Solution Factory (ASF) team supporting U.S. Customs and Border Protection (CBP) in Northern Virginia. In this role you will serve as the technical lead for a newly formed, three-person Computer Vision pod. Your team will design, train, and deploy custom YOLO object-detection models built from scratch to process live Full-Motion Video (FMV) feeds, automatically detecting and classifying roads, vehicles, people, and custom tactical assets. You will own the offline training pipeline, set data curation and annotation standards for production-captured datasets, and mentor two mid-level engineers as they build high-performance, low-latency inference models.\r\nKey Responsibilities\r\nTechnical Leadership: Lead a three-person AI/ML engineering team; set technical direction, sprint goals, coding standards, and model evaluation metrics.\r\nCustom YOLO Architecture: Design, modify, and train custom YOLO architectures from scratch, tuned for the environments, resolutions, and conditions found in CBP FMV feeds.\r\nEnd-to-End Pipeline: Architect the pipeline that ingests, cleans, and pre-processes production-recorded video into a secure training/sandbox environment.\r\nData Strategy: Define annotation and labeling guidelines, manage dataset curation, and address challenges such as class imbalance, varying weather, and low-contrast scenes.\r\nPerformance Optimization: Improve inference speed (FPS) and accuracy (mAP, precision, recall) using hardware-acceleration toolkits such as NVIDIA TensorRT, DeepStream, and CUDA.\r\nSystem Integration: Partner with video streaming engineers, software engineers, and system architects to integrate the live CV inference pipeline into the broader application.\r\nAgile Delivery: Serve as the primary point of contact for the AI/ML pod, translating system requirements into technical tasks within an Agile/Scrum environment.\r\nRequired Qualifications\r\nU.S. Citizenship and the ability to pass a CBP background investigation, which includes, but is not limited to:\r\n3-year check for felony convictions\r\n1-year check for illegal drug use\r\n1-year check for misconduct such as theft or fraud\r\nBachelor's, Master's, or Ph.D. in Computer Science, Data Science, Electrical Engineering, or a related field with an AI/ML focus.\r\n7+ years of related technical experience, including 4+ years developing and deploying deep learning / computer vision models with a strong focus on object detection.\r\nMust be local to the Northern Virginia area and able to work a hybrid schedule in Ashburn, VA.\r\nRequired Technical Experience\r\nDeep learning frameworks (PyTorch preferred; TensorFlow) and computer vision libraries such as OpenCV.\r\nAdvanced implementation and fine-tuning of the YOLO family of models (e.g., Ultralytics YOLOv8/v9/v10, custom YOLO backbones).\r\nTraining deep learning models from scratch, including custom anchor box design, loss function modification, and hyperparameter tuning.\r\nGPU-accelerated computing with NVIDIA CUDA, cuDNN, TensorRT, or ONNX.\r\nWorking with video streams (RTSP, HLS, files) and frame-by-frame processing.\r\nExpert-level Python, with clean, modular, and optimized code.\r\nData curation, active learning, and using/managing annotation tools (e.g., CVAT, Label Studio, Roboflow).\r\nDesired Qualifications\r\nMulti-object tracking (MOT) algorithms such as DeepSORT or ByteTrack.\r\nCloud-based AI infrastructure (AWS SageMaker, EC2 GPU instances).\r\nDeploying models to edge devices (NVIDIA Jetson, tactical hardware).\r\nPrior work with federal agency datasets or with U.S. Customs and Border Protection (CBP).","company":"Cdit","rawCompany":"cdit","city":"Ashburn","state":"VA","isRemote":false,"isActive":true,"createdAt":"2026-11-20T01:38:58.949Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"AI/ML Engineer (Computer Vision)","description":"Senior AI/ML Computer Vision EngineerCDIT is seeking a Senior AI/ML Computer Vision Engineer with Agile experience to join the BEAGLE (Border Enforcement Applications for Government Leading-Edge Information Technology) Agile Solution Factory (ASF) team supporting U.S. Customs and Border Protection (CBP) in Northern Virginia. In this role you will serve as the technical lead for a newly formed, three-person Computer Vision pod. Your team will design, train, and deploy custom YOLO object-detection models built from scratch to process live Full-Motion Video (FMV) feeds, automatically detecting and classifying roads, vehicles, people, and custom tactical assets. You will own the offline training pipeline, set data curation and annotation standards for production-captured datasets, and mentor two mid-level engineers as they build high-performance, low-latency inference models.\r\nKey Responsibilities\r\nTechnical Leadership: Lead a three-person AI/ML engineering team; set technical direction, sprint goals, coding standards, and model evaluation metrics.\r\nCustom YOLO Architecture: Design, modify, and train custom YOLO architectures from scratch, tuned for the environments, resolutions, and conditions found in CBP FMV feeds.\r\nEnd-to-End Pipeline: Architect the pipeline that ingests, cleans, and pre-processes production-recorded video into a secure training/sandbox environment.\r\nData Strategy: Define annotation and labeling guidelines, manage dataset curation, and address challenges such as class imbalance, varying weather, and low-contrast scenes.\r\nPerformance Optimization: Improve inference speed (FPS) and accuracy (mAP, precision, recall) using hardware-acceleration toolkits such as NVIDIA TensorRT, DeepStream, and CUDA.\r\nSystem Integration: Partner with video streaming engineers, software engineers, and system architects to integrate the live CV inference pipeline into the broader application.\r\nAgile Delivery: Serve as the primary point of contact for the AI/ML pod, translating system requirements into technical tasks within an Agile/Scrum environment.\r\nRequired Qualifications\r\nU.S. Citizenship and the ability to pass a CBP background investigation, which includes, but is not limited to:\r\n3-year check for felony convictions\r\n1-year check for illegal drug use\r\n1-year check for misconduct such as theft or fraud\r\nBachelor's, Master's, or Ph.D. in Computer Science, Data Science, Electrical Engineering, or a related field with an AI/ML focus.\r\n7+ years of related technical experience, including 4+ years developing and deploying deep learning / computer vision models with a strong focus on object detection.\r\nMust be local to the Northern Virginia area and able to work a hybrid schedule in Ashburn, VA.\r\nRequired Technical Experience\r\nDeep learning frameworks (PyTorch preferred; TensorFlow) and computer vision libraries such as OpenCV.\r\nAdvanced implementation and fine-tuning of the YOLO family of models (e.g., Ultralytics YOLOv8/v9/v10, custom YOLO backbones).\r\nTraining deep learning models from scratch, including custom anchor box design, loss function modification, and hyperparameter tuning.\r\nGPU-accelerated computing with NVIDIA CUDA, cuDNN, TensorRT, or ONNX.\r\nWorking with video streams (RTSP, HLS, files) and frame-by-frame processing.\r\nExpert-level Python, with clean, modular, and optimized code.\r\nData curation, active learning, and using/managing annotation tools (e.g., CVAT, Label Studio, Roboflow).\r\nDesired Qualifications\r\nMulti-object tracking (MOT) algorithms such as DeepSORT or ByteTrack.\r\nCloud-based AI infrastructure (AWS SageMaker, EC2 GPU instances).\r\nDeploying models to edge devices (NVIDIA Jetson, tactical hardware).\r\nPrior work with federal agency datasets or with U.S. Customs and Border Protection (CBP).","datePosted":"2026-11-20T01:38:58.949Z","dateModified":"2026-11-20T01:38:58.949Z","hiringOrganization":{"@type":"Organization","name":"Cdit","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Ashburn","addressRegion":"VA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"ceee82358a86eca97ade68d1"},"url":"https://jobsearcher.com/jobs/ceee82358a86eca97ade68d1"}}