Senior MLOps Engineer - Edge

Salary: £31,000 - 67,000 per year

Requirements:

• Production MLOps expertise, including experience building and operating pipelines that deploy models to production, with deep experience in CI/CD, containerization (Docker), and Linux systems.
• Hands-on experience compiling and optimising models for embedded hardware, ideally with TensorRT, and understanding the practical implications of precision, quantisation, and engine validation at scale.
• Ability to collaborate effectively with researchers and low-level embedded engineers to translate constraints into solutions.
• Systems thinking, including the ability to design architectures that handle failure gracefully and understand the implications of deploying to 10,000 heterogeneous devices.
• Experience managing risk via canary releases and safe rollbacks.
• A bias toward action and the initiative to fill gaps and solve problems as needed.
• Experience with the NVIDIA edge ecosystem, such as Jetson Orin, DeepStream SDK, and TensorRT, is a plus.
• Familiarity with video pipelines, GStreamer, or ffmpeg is a plus.
• Experience with fleet management tools like AWS IoT Greengrass, Balena, or custom OTA / fleet management solutions is a plus.
• Interest in sports technology, video analytics, or performance metrics is a plus.
• Wed like to hire someone who lives near our offices in London or Barcelona, but we are also open to remote candidates in the UK and Spain.

Responsibilities:

• Build and scale the machine learning infrastructure that powers Focus, our line of smart cameras.
• Own the edge deployment pipelines that transport neural networks from training clusters to tens of thousands of devices globally.
• Contribute to the platform that compiles trained models into optimised inference engines for devices like the Jetson Orin.
• Design, develop, and maintain the delivery systems that enable us to deploy models to fleets of devices.
• Build and maintain the pipeline that takes trained models and produces optimised, hardware-specific inference engines.
• Manage TensorRT compilation, precision trade-offs, calibration, and engine validation to ensure models run reliably and efficiently on target devices.
• Collaborate with Data Scientists, Embedded Engineers, and Product Managers to ensure smooth integration of complex features and capabilities.
• Implement infrastructure to silently test candidate models on production devices.
• Build telemetry pipelines to monitor drift, thermal impact, and inference latency in the wild.
• Build resilient update mechanisms for low-bandwidth environments.
• Optimise for limited storage and ensure devices recover gracefully from network failures.
• Share expertise to establish best practices in Python tooling, Infrastructure-as-Code, and CI/CD.
• Guide the team toward a more robust, automated future.

Technologies:

• AWS
• CI/CD
• Docker
• Embedded
• Hardware
• IoT
• Support
• Linux
• Machine Learning
• MLOps
• Network
• Python
• Cloud
• AI

More:

We build great teams and support the lifelong impact sports can have by helping teams around the world see their game differently. Our products make it easier for coaches and athletes at any level to capture video, analyze data, share highlights, and more. We trust our people to work their way and offer a culture of support, autonomy, career growth, and wellbeing. We provide flexible vacation time, company-wide holidays and meeting-free days, remote work options, and resources for professional development. Depending on location, we offer medical and retirement benefits, and we also provide an Employee Assistance Program and employee resource groups. We are an equal opportunity employer and foster an inclusive environment where everyone can belong. This role is for our Hardware Group, with candidates ideally near our offices in London or Barcelona, though we are also open to remote candidates in the UK and Spain.

last updated 35 week of 2026