SRE, Staff AI Infrastructure Engineer

About the role

You will work across Kubernetes, cloud, identity, secrets, networking, telemetry, incident management and automation to provide the production foundation for Arm's AI platform. You will initially contribute in three key areas: Build/deploy and operate the infrastructure for centrally hosted AI platform services, including MCP server infrastructure, model gateway services and supporting control-plane components.

What you'll do

• Own reliability, scalability, monitoring, alerting, incident response, runbooks and operational readiness for AI platform components
• Develop automation for provisioning, deployment, configuration, backup, recovery, patching, upgrades and lifecycle management
• Implement secure runtime patterns, including workload isolation, secrets management, identity integration, network controls and auditability
• Participate in production support and our paid on-call rota for high impact incident response
• Strong experience deploying and operating production infrastructure or platform services in a Linux-based environment using Kubernetes, containers

What you need

• 10–18 yrs of experience
• Terraform
• Kubernetes
• Linux
• Python
• Incident response
• LLMs
• Any graduate

Good to have

• Demand planning
• Vulnerability assessment
• Go
• Operational risk