Open to opportunities

James Josey

@jamesjosey

Computer Vision engineer building AI systems for video analysis, real-time tracking, and content intelligence using OpenCV, YOLO, and Python

United States

Message

I’m a Computer Vision and AI engineer specializing in video analytics, real-time processing, and intelligent content analysis systems. I’ve built scalable pipelines that process thousands of hours of video, extracting transcripts, keyframes, and on-screen text using tools like OpenCV, FFmpeg, YOLO, and Whisper. My experience includes CCTV/IP camera integration, RTSP streaming, and developing low-latency object detection and tracking systems.

I’ve also worked on AI-driven content analysis for social media, helping creators optimize engagement through data-backed insights. I enjoy designing clean APIs and backend systems (Python, Node.js) that integrate seamlessly with AI models and LLMs.

I’m particularly interested in building tools that bridge the gap between raw video data and actionable intelligence, enabling smarter automation and decision-making.

Experience

Work history, roles, and key accomplishments

Senior Computer Vision Engineer

VisionTrack AI

Jan 2022 - Feb 2026 (4 years 1 month)

- Designed and deployed real-time video analytics systems using YOLOv5/v8 for object detection across CCTV networks
- Built scalable RTSP ingestion pipelines handling 500+ concurrent camera streams
- Developed automated event detection (intrusion, motion, anomaly detection)
- Integrated OpenCV + FFmpeg pipelines for frame extraction and processing

Computer Vision YOLO Real Time Systems Object Detection OpenCV FFMPEG

AI Video Engineer

Streamlytics Labs

Mar 2020 - Dec 2021 (1 year 9 months)

- Built video content analysis tools for marketing and social media platforms
- Implemented OCR pipelines for extracting on-screen text from video ads
- Developed speech-to-text pipelines using Whisper and custom NLP post-processing
- Created APIs for structured video metadata extraction
- Delivered a project analyzing 10,000+ marketing videos for engagement insights

OCR Integration NLP Video Analytics Metadata Intelligent Metadata Extraction Engagement

Computer Vision Engineer

NexaVision Systems

Jun 2018 - Feb 2020 (1 year 8 months)

- Developed object tracking systems for warehouse automation
- Built vehicle detection and counting systems using deep learning
- Optimized video pipelines for edge devices (Jetson Nano)
- Delivered real-time monitoring dashboards for logistics operations
- Reduced manual monitoring workload by 60%

Multi Object Tracking Warehouse Automation Pipeline Development Edge Devices Real Time Systems

Full Stack Developer

CodeBridge Solutions

Jan 2017 - May 2018 (1 year 4 months)

- Built backend APIs using Python and Node.js for AI applications
- Integrated video processing features into web platforms
- Developed WordPress-based dashboards for analytics visualization
- Created REST APIs for media upload and processing
- Delivered multiple client projects involving video automation workflows

Python NodeJS Video Processing REST APIs