Senior MLOps Engineer (Azure Kubernetes Platform)

Duration: 31/03/2027

Rate up to £450 inside IR35

2-3 days in office in London

Role Overview

We are seeking an experienced Senior MLOps Engineer to support the design, implementation, and optimisation of enterprise-scale MLOps platforms on Microsoft Azure. Working closely with Solution and Enterprise Architects, the successful candidate will help build and operate scalable machine learning platforms on Kubernetes, with a focus on model lifecycle management, observability, low-latency inference, platform reliability, and cost efficiency.

Key Responsibilities

- Partner with Architects to design and implement end-to-end MLOps solutions on Azure.

- Build and operate scalable ML platforms using Azure Kubernetes Service (AKS) and cloud-native technologies.

- Develop CI/CD and Continuous Training (CT) pipelines for machine learning workloads.

- Deploy, manage, and optimise ML workloads in Kubernetes environments.

- Implement model serving capabilities that meet high-availability and low-latency requirements.

- Configure autoscaling, traffic management, rollback strategies, and resource governance.

- Manage containerised ML applications using Docker, Kubernetes, Helm, and GitOps practices.

- Implement monitoring and observability across:

- Model performance and drift

- Application performance and platform health

- Infrastructure and operational metrics

- Leverage Azure services including Azure Machine Learning, AKS, Azure Monitor, Application Insights, and Azure DevOps/GitHub Actions.

Performance & Cost Optimisation

- Optimise cloud infrastructure utilisation and spend for ML workloads.

- Implement efficient compute and scaling strategies across training and inference environments.

- Drive FinOps practices, cost visibility, and resource right-sizing.

- Improve platform performance, reliability, throughput, and latency.

Required Skills & Experience

- 4+ years' experience in Software Engineering, Platform Engineering, DevOps, or MLOps.

- 4+ years' experience building and operating production MLOps platforms.

- Strong hands-on experience with Azure-based MLOps architectures and AKS.

- Deep expertise in Kubernetes, containerisation, and model deployment patterns.

- Experience implementing monitoring, observability, and model lifecycle management.

- Hands-on experience with CI/CD pipelines and Infrastructure as Code.

- Experience with Azure Monitor, Application Insights, Azure DevOps, and/or GitHub Actions.

- Proficiency with Terraform, Bicep, or equivalent.

- Strong Python and Scripting skills.

- Experience supporting low-latency ML inference workloads and cloud cost optimisation initiatives.

Job Details

Company
Cyberteam
Location
London, United Kingdom
Employment Type
Contract
Salary
GBP 450 Annual
Posted