> Markdown version of [/jobs/ext/3437730-lead-ai-ml-engineer-computer-vision](https://www.wearedevelopers.com/jobs/ext/3437730-lead-ai-ml-engineer-computer-vision). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Lead AI/ML Engineer (Computer Vision)

- **Company:** Caci Inc
- **Location:** Ashburn, VA, United States
- **Experience:** Expert
- **Salary:** $103,800.0 - $218,100.0
- **Contract:** Permanent contract
- **Skills:** Agile Methodology, Artificial Intelligence, Amazon Web Services, Amazon Elastic Compute Cloud, Computer Vision, Cloud Engineering, Nvidia CUDA, Python (Programming Language), Machine Learning, Object Detection, OpenCV, Performance Tuning, Scrum Methodology, Tensorflow, Smart Devices, Software Requirements Analysis, Systems Integration, Pytorch, Deep Learning, Model Validation, Data Strategy, RTSP, Information Technology, ONNX (Open Neural Network Exchange) Format, Machine Learning Operations, TensorRT, Video Streaming, Data Pipelines
- **Published:** September 20, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=cfa18faa76d0026e

## About the Role

Required:

· Must be a U.S. Citizen with the ability to pass a CBP background investigation. Criteria include, but are not limited to:

o 3-year check for felony convictions

o 1-year check for illegal drug use

o 1-year check for misconduct such as theft or fraud

· Education: Bachelor's, Master's, or Ph.D. in Computer Science, Data Science, Electrical Engineering, or a related field with an AI/ML focus.

· Professional Experience: 7+ years of related technical experience, with 4+ years of dedicated experience developing and deploying Deep Learning/Computer Vision models (with a heavy focus on object detection).

· Location: Local candidates must be available to work a hybrid schedule in Ashburn, VA.

Experience with:

· Deep learning frameworks ( PyTorch preferred, TensorFlow) and Computer Vision libraries ( OpenCV ).

· Advanced implementation and fine-tuning of the YOLO family of models (e.g., Ultralytics YOLOv8/v9/v10, Custom YOLO backbones).

· Training deep learning models from scratch, including custom anchor box design, loss function modification, and hyperparameter tuning.

· GPU-accelerated computing using NVIDIA CUDA, cuDNN, TensorRT , or ONNX.

· Working with video streams (RTSP, HLS, files) and frame-by-frame processing.

· Programming in Python (expert level) and writing clean, modular, and optimized code.

· Data curation, active learning, and experience using/managing annotation tools (e.g., CVAT, LabelStudio, Roboflow).

Desired:

· Experience with multi-object tracking (MOT) algorithms (e.g., DeepSORT, ByteTrack).

· Familiarity with cloud-based AI infrastructure ( AWS SageMaker , EC2 GPU instances).

· Experience deploying models to edge devices (NVIDIA Jetson, tactical hardware).

· Prior experience working with federal agency datasets or Customs and Border Protection (CBP).

## Description

As the Senior AI/ML Engineer and Team Lead for our newly formed Computer Vision team, you will lead a dedicated 3-person pod focused on designing, training, and deploying custom, state-of-the-art YOLO models from scratch. Your team will process live Full-Motion Video (FMV) feeds to automatically detect and parse critical objects (roads, vehicles, people, and custom tactical assets). You will architect the offline training pipeline, define data curation and annotation standards for production-captured datasets, and guide two mid-level engineers in building high-performance, low-latency inference models.

· Technical Leadership: Lead a 3-person AI/ML engineering team, defining technical direction, sprint goals, code standards, and model evaluation metrics.

· Custom YOLO Architecture: Design, modify, and train custom YOLO architectures from scratch, optimized specifically for the unique environment, resolutions, and challenges of CBP's FMV feeds.

· End-to-End Pipeline Architecture: Architect the pipeline to ingest, clean, and pre-process production-recorded video data into a secure training/sandbox environment.

· Data Strategy: Define annotation/labeling guidelines, manage dataset curation, and implement strategies to handle challenges like class imbalance, varying weather conditions, and low-contrast environments.

· Performance Optimization: Optimize model inference speed (FPS) and accuracy (mAP, Precision, Recall) using hardware-acceleration toolkits (e.g., NVIDIA TensorRT, DeepStream, CUDA).

· System Integration: Collaborate with Video Streaming Engineers, Software Engineers, and System Architects to integrate the live CV inference pipeline with the broader application.

· Agile Team Delivery: Act as the primary POC for the AI/ML pod, translating system requirements into technical tasking within our Agile/Scrum environment.