- Own and evolve a cloud-native Azure & Kubernetes platform at scale
- Partner with engineering teams to run model-driven, production services
About Our Client
This opportunity is with a large organisation in the financial services industry.
Job Description
- Design, build, and manage production infrastructure on Microsoft Azure with Kubernetes as the core orchestration platform.
- Operate, monitor, and scale Kubernetes-based services, leading incident response and reliability improvements.
- Partner with algorithm and application teams to deploy and run model-serving and inference workloads in production.
- Build and refine CI/CD pipelines (e.g. GitHub Actions, Azure DevOps, GitLab CI) to enable fast, reliable releases.
- Champion infrastructure-as-code, DevOps best practices, and enhanced observability across the engineering stack.
The Successful Applicant
- Significant experience as a DevOps, Platform, or SRE Engineer supporting large-scale, production systems.
- Deep hands-on expertise with Azure services, Kubernetes, and observability tooling for distributed systems.
- Proven track record building and maintaining CI/CD pipelines and automating infrastructure through code.
- Comfortable collaborating with software and algorithm teams on model-related or AI-driven services; LLM or GPU
What's On Offer
- End-to-end ownership of a high-impact Azure/Kubernetes platform, with direct influence over architecture, tooling, and DevOps practices.
- Cutting-edge exposure to AI/ML and potentially LLM and GPU-based workloads, working closely with algorithm and product teams in real production environments
Contact
James Jefferson
Quote job ref
JN-022026-6937880
