Senior ML Ops Engineer

Department: Platform Delivery

Employment Type: Permanent - Full Time

Location: London

In this role you will work in the Platform team - a function for the deployment and evolution of the backend platform that underpins the core of the Xantura business.

• Continuously evolve the platform infrastructure powering all AI services (predictive modelling, NLP, knowledge representation, and agentic AI), ensuring reliable, scalable operation across a growing base of local authority clients.
• Deploy and manage ML models via Azure ML endpoints, batch endpoints, and AKS, enabling resilient, secure model hosting that accelerates client onboarding and ensures models remain performant and monitorable throughout their lifecycle.
• Ensure all ML systems are transparent, explainable, and auditable, aligned with Responsible AI principles and UK GDPR; essential where AI outputs inform decisions about vulnerable people in health and social care.
• Design, build, and maintain production grade orchestration pipelines (Dagster) supporting model training, inference, and retraining, ensuring data from local authority systems is timely, accurate, and fit for purpose before it reaches ML services.
• Contribute to organisation wide AI capability building, sharing best practice with delivery and consulting teams, advising on technical feasibility, and shaping governance standards as the AI function scales.

We'd love to hear from you if you have:

• Bachelor's or Master's degree in Computer Science, Software Engineering, or a related technical field, or equivalent practical experience.
• 4+ years of professional experience in an MLOps, Platform Engineering, or Infrastructure Engineering role supporting ML or data intensive systems.
• Strong programming skills and production experience in Python.
• Expertise in Azure native MLOps, including model endpoints, pipelines, registries, environments, and compute management.

Clear evidence of practical experience across the following:

• Deploying, scaling, and troubleshooting containerised workload on Kubernetes in production
• Building and maintaining CI/CD pipelines (Azure DevOps or equivalent) for automated testing, building, and deployment of ML services
• Implementing infrastructure as code (Terraform, Bicep or Pulumi)
• Implementing monitoring and observability for production systems, including metrics, alerting, logging, and dashboarding (e.g. Prometheus, Grafana)
• Pipeline orchestration using Dagster, Airflow, Prefect, or similar

• Practical experience with model serving infrastructure - batch and/or real time inference at scale.
• Experience operating multi tenant systems, particularly scaling infrastructure across multiple clients or business units.
• Practical experience building and serving production ready, asynchronous APIs for embedding and/or other compute intensive services.
• Experience setting up, and optimising vector databases, e.g. Qdrant, and integrating with other services
• Proficiency in Python for building high performance data and model pipelines, with strong software engineering discipline (testing, versioning, CI/CD).
• Deep familiarity with the Azure ecosystem (Azure Kubernetes Service, Azure Container Registry, Azure DevOps, Azure Blob Storage, Azure Monitor, Azure Key Vault).

Location - This is a hybrid role based in our office in London (Borough). You would be expected to be able to work from the office at least 1 2 days per week. Some travel is also required for on site client engagements as needed.

• Competitive salary reviewed annually
• Work for a passionate, mission driven company solving society's big problems
• Work flexible hours around life commitments with a focus on delivering company value rather than hours worked
• Ability to work remotely (excluding face to face Team Meetings and client meetings)
• Training and development opportunities
• 25 days annual leave (plus bank holidays)
• Company pension
• Private medical insuranceGenerous enhanced parental leave policies
• Cycle to work scheme
• Flu Vaccinations
• Eye Test and contribution towards Glasses for VDU use
• Employee Assistance Programme
  • Mental health and wellbeing support
  • Remote GP access
  • Counselling/therapy
  • Physiotherapy
  • Medical second opinions