- Own day-2 production operations of a large-scale, AI-first platform on GCP.

- Run, scale, and harden GKE-based workloads integrated with a broad set of GCP managed services (data, messaging, AI, networking, and security).

- Define, implement, and operate SLIs, SLOs, and error budgets across platform and AI services.

- Build and own New Relic observability end-to-end (APM, infrastructure, logs, alerts, dashboards).

- Improve and maintain CI/CD pipelines and Terraform-driven infrastructure automation.

- Operate and integrate Azure AI Foundry for LLM deployments and model lifecycle management.

- Lead incident response, postmortems, and drive systemic reliability improvements.

- Optimize cost, performance, and autoscaling for AI and data-intensive workloads.

Requirements :

- 6+ years of hands-on experience in DevOps, SRE, or Platform Engineering roles.

- Strong, production-grade experience with GCP, especially GKE and core managed services.

- Proven expertise running Kubernetes at scale in live environments.

- Deep hands-on experience with New Relic in complex, distributed systems.

- Experience operating AI/ML or LLM-driven platforms in production environments.

- Solid background in Terraform, CI/CD, cloud networking, and security fundamentals.

- Comfortable owning production systems end-to-end with minimal supervision.