About this role
Salary: £? - ? per year
Requirements: Strong experience as a Senior or Lead Platform Engineer / DevOps EngineerDeep hands-on experience building and operating Kubernetes-based platformsStrong practical experience using Helm and infrastructure-as-code tools such as TerraformProven experience extending Kubernetes with higher-level platforms and services, rather than treating it as an end in itselfStrong understanding of operational concerns: monitoring, logging, incident response, reliability and maintenanceConfidence working directly with engineers and data scientists to support real workloads in productionMLOps experience is highly desirable, including exposure to tools and patterns such as Kubeflow or comparable approachesExperience operating model serving and inference platforms such as KServe, vLLM, or comparable solutionsExperience supporting LLM-based workloads, including optimisation and serving considerationsExperience providing notebook-based development environments such as JupyterHub within secure platformsExposure to emerging tooling such as InstructLab, trustworthy AI tooling, or equivalent approaches Responsibilities: Provide technical leadership across platform engineering, DevOps, and MLOps activitiesDesign, build, and operate a Kubernetes-based MLOps platform that supports the full model lifecycleImplement and operate MLOps tooling and frameworks enabling teams to build, train, deploy, and serve modelsDevelop and support model serving and inference capabilities within Kubernetes environmentsImplement workflows that support model experimentation, including notebooks, packaging, deployment and versioningEnable scalable inference and LLM-based workloads, including serving and optimisation considerationsWork with data scientists and ML engineers to ensure the platform is usable, well documented and fit for purposeOwn platform operability, reliability, security and supportability in live production environmentsTroubleshoot complex platform, workload and deployment issues across Kubernetes and MLOps layersContribute to architectural decisions while remaining deeply hands-on in delivery Technologies: AIDevOpsHelmSupportKubeflowKubernetesLLMSecurityTerraform More:
We operate in production-focused environments where platform usability and operational excellence matter. Our work sits at the intersection of platform engineering, DevOps and MLOps, with close collaboration across data science, ML engineering, software engineering and architecture. We are looking for someone who is comfortable working in the weeds, understanding how platforms behave under real workloads, and designing guardrails that balance flexibility for users with reliability, security and governance. In return, you will play a key role in enabling AI delivery at scale by building platforms that other engineers and data scientists actually want to use. This is an opportunity to lead technically, shape a practical MLOps platform, and own operational outcomes in production environments where reliability and usability matter. We are committed to fostering an equitable, diverse and inclusive workplace, where every employee and contractor feels valued and empowered. We actively seek to recruit talent from all backgrounds and believe that respect and inclusion lead to innovative solutions and exceptional outcomes.
last updated 29 week of 2026