> Markdown version of [/jobs/ext/1926893-computer-vision-engineer](https://www.wearedevelopers.com/jobs/ext/1926893-computer-vision-engineer). 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

- **Company:** Mustard Systems
- **Location:** London, UK (Remote available)
- **Experience:** Expert
- **Salary:** £45,120.0
- **Contract:** Permanent contract
- **Skills:** Computer Vision, Object Detection
- **Published:** August 5, 2026
- **Apply:** https://www.adzuna.co.uk/jobs/details/5826789449

## About the Role

* Strong experience building and deploying computer vision models in production.
 * Expertise in areas such as object detection, tracking, pose estimation, action recognition, or temporal event detection.
 * Confidence working autonomously and leading and owning technical decisions.
 * Ability to collaborate with Quant researchers, cricket domain experts, and data engineers.
 * A pragmatic mindset-balancing research exploration with delivery.

## Description

We're looking for a Senior Computer Vision Engineer to join our Data Team and help build the next generation of cricket analytics at Mustard. You'll be responsible for extracting high-value data from both historical and live cricket footage, ensuring the data is accurate, scalable, and ready for our Quant team to turn into powerful insights.

As the senior computer vision expert in the company, you'll lead technical decisions, define best practices, and shape the future of CV at Mustard. You'll work closely with our Cricket Team, who have built a manual data collection system, and your work will be central to automating and elevating the entire pipeline.

If you love solving complex CV problems and want to apply your skills to the world of sports analytics, this is the role for you.

What You'll Do

Build Cricket Video Extraction Systems

 * Develop computer vision models and pipelines that extract key data points from cricket broadcasts and replays.
 * Work across high-variation video sources, including different angles, inconsistent framing, and broadcast-quality footage.
 * Ensure that events in replay segments are not double-counted or falsely captured.

Ensure Data Quality & Verification

 * Build a robust framework to validate automatically extracted data against manually collected ground-truth data.
 * Work with the team to align definitions, rules, and edge cases.
 * Develop metrics, tests, and tools that ensure confidence and reliability in all extracted outputs.

Scale Systems Across the Entire Cricket Archive

 * Improve pipelines to support new data points and higher accuracy over time.
 * Scale systems to process large volumes of historical footage with consistent quality.
 * Identify opportunities to increase automation and reduce manual effort across the business., Cricket video presents a unique set of real-world challenges. You should be excited about solving problems like:
 * Replay handling: ensuring the system doesn't double-capture replayed events.
 * Variable camera angles: handling unpredictable broadcast camera changes.
 * Incomplete coverage: extracting meaningful data even when balls aren't shown clearly.
 * Broadcast-quality footage: dealing with noise, compression, zoom levels, and motion blur.


## Related Videos

- [From Collecting Bottle Caps 🥤to Building Vision 👀](https://www.wearedevelopers.com/videos/2028-from-collecting-bottle-caps-to-building-vision)
- [Focoos AI: Building the Future of Computer Vision](https://www.wearedevelopers.com/videos/1659-focoos-ai-building-the-future-of-computer-vision)
- [Machine Learning in ML.NET](https://www.wearedevelopers.com/videos/272-machine-learning-in-ml-net)
- [Computer Vision from the Edge to the Cloud done easy](https://www.wearedevelopers.com/videos/263-computer-vision-from-the-edge-to-the-cloud-done-easy)
- [How computers learn to see – Applying AI to industry](https://www.wearedevelopers.com/videos/756-how-computers-learn-to-see-applying-ai-to-industry)
- [Is it (F)ake?! Image Classification with TensorFlow.js](https://www.wearedevelopers.com/videos/1626-is-it-f-ake-image-classification-with-tensorflow-js)

## Related Articles

- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [Fully Remote Software Engineer Jobs](https://www.wearedevelopers.com/magazine/447-fully-remote-software-engineer-jobs)
- [Data Engineer Salary UK](https://www.wearedevelopers.com/magazine/253-data-engineer-salary-uk)
- [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)
- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)
- [Dev Digest 112 - The True Crime of AI Development](https://www.wearedevelopers.com/magazine/421-dev-digest-112-the-true-crime-of-ai-development)