AI/ML Engineer (Computer Vision)
CACI International1 day ago
Base Salary
$104k - $218k/yr
Responsibilities
- Lead a three-person computer vision AI/ML engineering pod and define technical direction, sprint goals, coding standards, and model evaluation metrics.
- Design, modify, train, and fine-tune custom YOLO architectures for object detection in CBP full-motion video feeds.
- Architect pipelines for ingesting, cleaning, preprocessing, and securely transferring production-recorded video data into training and sandbox environments.
- Define data annotation standards, manage dataset curation, and address class imbalance, weather variation, and low-contrast conditions.
- Optimize model inference speed and accuracy using GPU-acceleration toolkits and performance metrics.
- Integrate live computer vision inference pipelines with broader applications in collaboration with video streaming engineers, software engineers, and system architects.
- Translate system requirements into technical tasks and serve as the primary point of contact for the AI/ML pod in an Agile/Scrum environment.
Requirements
- U.S. citizenship and the ability to pass a CBP background investigation, including specified checks for felony convictions, illegal drug use, and misconduct.
- Bachelor’s, Master’s, or Ph.D. in Computer Science, Data Science, Electrical Engineering, or a related AI/ML-focused field.
- At least 7 years of related technical experience, including at least 4 years developing and deploying deep learning or computer vision models with a strong focus on object detection.
- Expert-level Python programming experience and the ability to write clean, modular, optimized code.
- Experience with PyTorch or TensorFlow, OpenCV, custom YOLO architectures, training models from scratch, custom anchor boxes, loss-function modification, and hyperparameter tuning.
- Experience with NVIDIA CUDA, cuDNN, TensorRT, or ONNX for GPU-accelerated computing.
- Experience processing video streams such as RTSP, HLS, and video files frame by frame.
- Experience with data curation, active learning, and annotation tools such as CVAT, LabelStudio, or Roboflow.
- Preferred experience with multi-object tracking algorithms such as DeepSORT or ByteTrack.
- Preferred familiarity with AWS SageMaker and EC2 GPU instances.
- Preferred experience deploying models to NVIDIA Jetson or other edge and tactical hardware.
- Prior experience with federal agency datasets or Customs and Border Protection is desired.
Benefits
- Full-time regular employee position with up to 10% local travel.
- Hybrid work schedule in Ashburn, Virginia for local candidates.
- Flexible time off and access to learning and development resources.
- Healthcare, wellness, financial, retirement, family support, continuing education, and time-off benefits.
Categories
About CACI International
CACI International is a public government contractor that delivers enterprise IT, cybersecurity, electronic warfare, space, and intelligence solutions to U.S. defense, intelligence, and federal civilian customers. It provides systems engineering, software and data services, and mission support across C4ISR and business systems, primarily through long-term government contracts. Founded in 1962 and headquartered in Reston, Virginia, CACI trades on the NYSE under the ticker CACI.