DevOps Engineer - AI Platform

About the Role

As DevOps Engineer you build and run the delivery pipeline and runtime for our AI platform, so the AI Development pods can build, test and release AI applications, models and agents quickly and safely.

Responsibilities

• Build and maintain infrastructure as code for the AI platform on Azure (AKS, container registry, API Management, networking and supporting services).
• Create CI/CD pipelines in Azure DevOps for AI applications, agents, models and prompts, including automated testing and evaluation gates before release.
• Set up separate development, test and production environments so teams can build and run controlled pilots.
• Implement monitoring, logging, tracing and alerting for AI applications, agents and model usage, including cost and token tracking.
• Manage releases, rollbacks and incident response, and support the platform's kill-switch and change-control processes.
• Automate routine operations and keep the platform patched, scalable and resilient.

Qualifications

• 5+ years in DevOps, site reliability or platform engineering.
• Strong hands-on experience with Azure, Kubernetes (AKS) and containers.
• Infrastructure as code with Terraform or Bicep.
• CI/CD pipeline design, ideally with Azure DevOps.
• Scripting in Python, PowerShell or Bash.
• Experience operating production systems with monitoring and on-call practices.

Preferred Skills

• Experience deploying LLM or ML workloads and managing model endpoints.
• Familiarity with LLM observability and evaluation tooling.
• Experience in a regulated industry with formal change management.
• Azure DevOps Engineer Expert or Kubernetes certification.

Our technology

• Microsoft Azure (AKS, API Management, Service Bus, Key Vault, Entra ID, Azure AI services), Snowflake, MCP servers, Python and .NET, Azure DevOps, and leading large language models.