MLOps Engineer

About

We have partnered with a ground-breaking, award-winning technology company building the future of sports talent identification and development. Our partner builds AI-driven tools that generate and analyse sports data, helping clubs, national federations and players unlock real-time analysis and valuable insights. Their technology is already in production and used at the highest level, including at global sporting events. They are now looking for an MLOps Engineer to join a small, fast-moving team and own the platform that takes their models from research into reliable, real-time production.

The Role

• Own the end-to-end ML deployment lifecycle, taking computer vision models from experimentation to production quickly, safely and repeatably.
• Design, build and maintain CI/CD pipelines for model training, validation, packaging and release.
• Build and optimise scalable inference pipelines for large-scale video processing across edge and cloud environments, with a focus on latency, throughput and cost.
• Own model serving and deployment infrastructure on AWS (e.g. ECR, Lambda, S3, ECS/EKS, SageMaker or equivalent), managed through infrastructure-as-code (Terraform, CloudFormation or CDK).
• Implement model monitoring for performance degradation, data drift and system health, with automated alerting and retraining triggers.
• Put in place experiment tracking, model versioning and a model registry so that every deployed model is reproducible and auditable.
• Work closely with ML engineers and sport scientists to make models production-ready: profiling, optimisation (e.g. quantisation, ONNX/TensorRT) and robust testing.
• Champion engineering best practice across the team, including observability, automation, documentation and reliable release processes.

What You’ll Need

• Proven experience deploying and operating ML models in real-world, high-stakes production environments.
• Strong DevOps and MLOps background: CI/CD (e.g. GitHub Actions, GitLab CI), containerisation (Docker) and orchestration (Kubernetes/ECS).
• Hands-on AWS experience and infrastructure-as-code tooling (Terraform, CloudFormation or CDK).
• Experience with MLOps tooling such as MLflow, Weights & Biases, Kubeflow, SageMaker Pipelines or similar.
• Experience building or scaling inference pipelines for image or video data, ideally including edge or GPU-accelerated deployment.
• Familiarity with model monitoring and observability (e.g. Prometheus, Grafana, CloudWatch, Evidently).
• Strong Python skills and a working knowledge of deep learning frameworks (PyTorch, TensorFlow) and computer vision libraries (e.g. OpenCV).
• Strong software engineering fundamentals: version control, testing, code review and documentation.
• Experience working in a start-up or fast-paced, high-autonomy environment.
• Degree in Computer Science, Engineering or a related field; an MSc or PhD is a plus but not essential.