We're looking for a Computer Vision Expert who has taken object detection and video analytics all the way into production — not just in notebooks, but running on real CCTV streams in real environments. You'll design, build, and optimise the algorithms that turn raw video into automated detection, tracking, recognition, and event analysis, and you'll help bring that intelligence into our client's wider ecosystem of applications. This is hands-on work on large-scale, real-world video. If you're equally comfortable reaching for a classical computer vision technique or a deep learning model depending on what the problem actually needs, and you care about latency and accuracy as much as the science, you'll feel at home here. What you'll do Develop classical and AI-based computer vision algorithms for CCTV footage — object detection, tracking, and anomaly/event detection. Integrate the CCTV solution into the broader ecosystem of applications it needs to talk to. Work closely with software teams to make sure both edge and cloud-based solutions run efficiently. Measure what matters — accuracy, latency, scalability — and optimise systems for real-time deployment. What you bring A Master's or PhD in Computer Science, Electrical Engineering, Artificial Intelligence, or a related field. Strong, demonstrable experience in computer vision, image/video processing, and machine learning. Proficiency with deep learning frameworks — TensorFlow, PyTorch, OpenCV, and similar. Solid programming skills in Python and C++ (Golang is a plus). Working knowledge of video streaming protocols such as RTSP and ONVIF. A genuine problem-solver's instinct, and the ability to work with real-world, large-scale video datasets. Nice to have Experience with real-time video analytics and edge computing for CCTV. A background in auto-labelling strategies such as model distillation. Optimisation experience for embedded systems and GPUs. An understanding of cybersecurity and privacy considerations in video surveillance. ATTENTION UPON DROPPING YOUR APPLICATION: Please, immediately send an email to [email protected] with subject 'Computer Vision Expert – Your Name' sharing concrete examples of computer vision and video analytics work you've done in production. We're specifically interested in: CCTV or video analytics systems you've built or shipped — the detection/tracking tasks, the scale of video you handled, and your specific role Object detection, tracking, or anomaly-detection models you've deployed — both classical and deep learning, and why you chose each Real-time and latency work — how you optimised a pipeline to run live, and the accuracy/latency trade-offs you navigated Edge or GPU/embedded deployment — what you ran where, and what you did to make it fit the hardware Hands-on experience with the stack: Python, C++, TensorFlow/PyTorch/OpenCV, and streaming protocols like RTSP or ONVIF Any auto-labelling, model distillation, or privacy/security work relevant to video surveillance Please point us to production work, not tutorials, side experiments, or course projects. A short paragraph per example is enough: what you built, your specific role, the scale or context it operated in, and one or two concrete decisions you made. Links to repos, demos, or write-ups are welcome where you can share them.