SRE, Staff AI Infrastructure Engineer
Core
Build and operate the runtime infrastructure for Arm's central AI control plane, ensuring safe, scalable, and efficient AI service delivery across engineering teams.
Role type
Staff SRE / Platform Engineer (AI Infrastructure)
Builds
Production AI runtime platforms, model gateway services, MCP server infrastructure, and control-plane components.
Domain
Semiconductor / AI Infrastructure / Cloud Native (via careerplan.io/jobs/99150464384-sre-staff-ai-infrastructure-engineer-at-arm)
Deliverable
production ML models
Required skills
Kubernetes, Infrastructure-as-Code (IaC), GitOps, Terraform, Go, Python, Incident Management, Security Fundamentals, Linux, Cloud Platforms, CI/CD
Preferred skills
Internal Developer Platforms, Service Mesh, Policy-as-Code, Workload Identity, Sandboxing, Multi-tenant Platform Designs, Regulated Environments, OpenAI Tools/APIs
Technologies
Kubernetes, Terraform, Go, Python, MCP, GitOps, Linux, Cloud
Responsibilities
Build/deploy and operate infrastructure for centrally hosted AI platform services; Design runtime patterns for isolation, scalability, and secure execution; Automate provisioning and lifecycle management; Define and implement SLOs, alerting, and dashboards; Lead incident response and post-incident reviews; Ensure platform components meet security and compliance expectations.
Seniority
Staff, hands-on IC