> Markdown version of [/jobs/ext/4797118-computer-vision-engineer-remote-hybrid-options-available](https://www.wearedevelopers.com/jobs/ext/4797118-computer-vision-engineer-remote-hybrid-options-available). 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). --- # Computer Vision Engineer - Remote & hybrid options available. - **Company:** Digital Camel Ltd - **Location:** Derby, United Kingdom - **Contract:** Permanent contract - **Skills:** Computer Vision, Python (Programming Language), Object Detection, OpenCV, Management of Software Versions, ONNX (Open Neural Network Exchange) Format, Machine Learning Operations, TensorRT, Video Analysis, Data Pipelines - **Published:** November 20, 2026 - **Apply:** https://www.totaljobs.com/job/computer-vision-engineer/digital-camel-ltd-job108353082 ## About the Role * Commercial computer vision experience, ideally with something shipped. * Strong Python, clean and tested code, and the full train/evaluate loop * Object detection, tracking and/or segmentation, plus OpenCV * Some exposure to deploying models (ONNX, TensorRT, quantisation, Jetson or similar) * A practical, commercial mindset: you care whether it works for the customer, not just the benchmark You don't need to tick every box. If you're strong in one area, such as edge deployment or model training will still want to speak with you. Backgrounds in automotive/ADAS, security and video analytics, people tracking, industrial inspection or robotics translate really well. ## Description You'll own the models already in production and make them better: detection, tracking and behaviour classification on real-world video, running on edge devices across alot of sites. It's messy data. * Maintain and improve production models for detection, tracking and behaviour recognition * Own retraining, versioning, data pipelines and deployment to cloud and edge devices * Monitor how models perform in the field and diagnose failures * Build the test sets and evaluation that show whether a change is safe to ship * Work with the in-house annotation team so model failures feed back into the data * Help new models move from experiment to production