15 days ago
Cambridge, United KingdomStaff+
Responsibilities
- Build, deploy, operate, and continuously improve production infrastructure for Arm’s AI platform services, including MCP servers, model gateways, and control-plane components.
- Design runtime patterns for workload isolation, scalability, secure execution, capacity management, and cost-aware operation.
- Automate provisioning, deployment, configuration, backup, recovery, patching, upgrades, and lifecycle management using infrastructure-as-code and GitOps patterns.
- Own reliability, scalability, monitoring, alerting, service-level indicators, service-level objectives, runbooks, and operational readiness.
- Implement secure runtime patterns covering secrets management, identity integration, network controls, auditability, vulnerability management, and access control.
- Participate in incident response, post-incident reviews, vendor outage handling, production support, and a paid on-call rota.
- Contribute technical leadership and input to platform roadmap planning and prioritization.
Requirements
- Expert-level experience deploying and operating production infrastructure or platform services in Linux-based environments using Kubernetes, containers, cloud or private-cloud platforms, infrastructure-as-code, and CI/CD or GitOps tooling.
- Very strong understanding of production platform security fundamentals, including identity, secrets, access control, network segmentation, vulnerability management, and audit logging.
- Familiarity with AI platform concepts such as model routing, MCP servers, agentic workflows, RAG systems, or LLM observability.
- Very strong automation and scripting skills using technologies such as Terraform, Go, Python, or similar.
- Experience with incident management, problem management, demand forecasting, and production readiness practices.
- Preferred experience operating internal developer platforms, AI platforms, model gateways, MCP infrastructure, or shared engineering platforms.
- Preferred experience with service mesh, policy-as-code, workload identity, sandboxing, secure runtime environments, multi-tenant platform designs, or regulated and security-sensitive engineering environments.
- Working knowledge of OpenAI tools, products, and APIs is desirable.
Benefits
- Hybrid working is available, with specific working patterns determined by the team and role.
- The role includes a paid on-call rota for high-impact incident response.
- Arm provides an inclusive environment focused on continuous learning and professional growth.
- Recruitment accommodations are available upon request and are handled confidentially.
About Arm
Arm’s foundational technology is defining the future of computing. A future built by the greatest technology ecosystem in the world. A future built on Arm. Arm is everywhere technology matters. Technology matters everywhere. Together, we’ll power every technology revolution moving forward, including cloud computing, automotive and autonomous systems, IoT, the metaverse, and beyond. Changing the world. Again. On Arm.