Machine learning engineer in sports data

We are looking for a Machine Learning Engineer to take our models from research into production. You will build the pipelines, services and monitoring that let them run reliably during live matches. You will work closely with our Data Scientists, who design the models, and with our .NET engineering teams, who build the wider platform. We are hiring mainly at senior level, and strong mid-level candidates are welcome.

• Build and maintain the pipelines that train, test and release our models, from raw data to production
• Package and serve models so they respond in real time during live matches, integrated with our .NET services (for example through ONNX Runtime)
• Build data ingestion and processing pipelines for high-volume, real-time sports data
• Set up experiment tracking, model versioning and a model registry, so every release is reproducible and traceable
• Monitor models in production for speed, stability and accuracy, with alerts during live matches
• Run our workloads on the major cloud providers (AWS, Azure, GCP, Alibaba Cloud…), using containers, orchestration and infrastructure-as-code
• Turn Data Scientists' prototypes into robust, tested, maintainable code
• Work closely with Data Scientists, .NET engineers and our data operations team to agree interfaces, quality thresholds and release criteria
• Contribute to code reviews and help raise and maintain engineering standards across the team

• 3–5 years of experience as a Machine Learning Engineer or in a similar role, with models running in production
• Strong C# / .NET experience building production services and APIs
• Experience integrating ML models into .NET applications (ONNX Runtime, ML.NET or similar)
• Experience serving models with tight latency requirements
• Hands-on MLOps experience: MLflow or an equivalent for tracking and model registry, Docker, Kubernetes, and CI/CD for ML
• Experience with at least one of the major cloud providers (AWS, Azure, GCP, Alibaba Cloud…)
• Experience working with time-series or sequential data at volume
• Fluent English, written and spoken
• driven to push the boundaries and lead change and performance
• communicative to leave no-one in the dark and to work with your team successfully
• reliable so we know that we can call on you to meet deadlines
• passionate about the latest technologies and standards
• proactive to suggest improvements, identify and fix potential issues
• solid technically speaking, to advise both Clients and internal teams
• Будет плюсом: Experience building high-throughput, low-latency .NET services (asynchronous processing, gRPC or similar); Basic Python skills, enough to read and work with Data Scientists' PyTorch and TensorFlow code; Experience with streaming or real-time systems (Kafka or similar); Experience with player-tracking, motion-capture or other location-over-time data, in sport or elsewhere; Experience with orchestration tools such as Airflow, Kubeflow or Argo; An interest in sport and its data

• This is a fully remote role.