Senior Platform Engineer

Senior Platform Engineer Build and operate the platforms that make AI and machine learning work at scaleWe're looking for a Senior Platform Engineer to join our team and play a key role in designing and operating the platform that underpins AI and machine learning delivery.This is a hands‐on senior platform role, focused on building robust, Kubernetes‐based platforms that enable MLOps engineers, ML engineers, and data scientists to deploy, run, and manage models safely and effectively in production.While you'll need a strong understanding of how machine learning and LLM workloads are trained, packaged, deployed, and served, this is not a "deploy models all day" role. Instead, your impact will come from creating the infrastructure, tooling, workflows, and guardrails that allow others to do that work reliably and at scale. What you'll be doing You'll be responsible for building a production‐grade AI / ML platform, not just running clusters.You will:Design, build, and operate a Kubernetes‐based platform that supports multiple ML and engineering teamsExtend Kubernetes with MLOps‐specific capabilities, rather than treating it as a finished productProvideplatform‐level support for:Model development and experimentationModel packaging, deployment, and promotionScalable inference and LLM‐based workloadsBuild shared platform services that enable consistent, repeatable model deployment, even where day‐to‐day deployment is owned by MLOps or ML engineersWork closely with data scientists and MLOps engineers to ensure the platform is genuinely usable and fit for purposeOwn platform operability, reliability, security, and lifecycle management in productionTroubleshoot complex issues that cut across infrastructure, Kubernetes, and MLOps layersContribute to architectural decisions while remaining hands‐on with implementation What we're looking for This role is ideal for someone who sees themselves first and foremost as a platform engineer, with the depth to support AI and ML workloads properly.Essential experience:Strong background as a Senior Platform Engineer or Senior DevOps EngineerDeep, hands‐on experience building and operating Kubernetes‐based platformsStrong practical experience with Helm and Infrastructure as Code (e.g. Terraform)Proven experience building internal platforms for other engineers, not just running workloadsStrong grasp of operational fundamentals: monitoring, logging, reliability, incidents, and maintainabilityComfortable collaborating closely with MLOps engineers and data scientists, even where responsibilities differ ML platform & MLOps knowledge (important) You don't need to be a full‐time MLOps engineer - but you do need practical understanding of how ML and AI workloads behave in production.Experience or exposure to areas such as:MLOps platforms (e.g. Kubeflow or similar frameworks)Model serving and inference platforms (e.g. KServe, vLLM, or equivalent)Supporting LLM‐based workloads, including performance and scaling considerationsNotebook environments such as JupyterHubAwareness of emerging tooling around Responsible / Trustworthy AI or comparable solutionsThis ensures you're building a platform that actually works for AI use cases - not a generic compute layer. Desirable experience Working in organisations with a clear AI or data platform strategySupporting data scientists or ML engineers at scaleExperience in regulated, secure, or high‐assurance environmentsDesigning platforms that balance flexibility, governance, and controlIf you enjoy solving hard platform problems and understand that AI places real, specific demands on infrastructure, this role gives you the space and responsibility to make a genuine impact. If interested, apply now!Guidant, Carbon60, Lorien & SRG - The Impellam Group Portfolio are acting as an Employment Business in relation to this vacancy.