Build and operate Arm’s production AI platform infrastructure, including MCP servers, model gateways, runtime services, and control-plane components. Develop scalable, secure, observable, and cost-aware platform patterns using Kubernetes, cloud infrastructure, infrastructure as code, and GitOps. Responsibilities include automation, monitoring, incident response, reliability engineering, secrets and identity management, network controls, auditability, lifecycle management, and participation in an on-call rotation.

Build and operate Arm’s production AI platform infrastructure, including model gateways, MCP services, and control-plane components. Own scalability, reliability, observability, security, incident response, automation, lifecycle management, and operational readiness. Develop infrastructure-as-code and GitOps workflows, secure runtime patterns, telemetry, monitoring, alerting, and support processes across Kubernetes, cloud, identity, networking, secrets, and compliance systems. Participate in a paid on-call rotation for high-impact incidents.