Responsibilities
Build and operate observability, telemetry, dashboards, alerts, and cost attribution for LLM gateways, models, agents, and AI platform services. Operate secure AI platform services on Kubernetes, establish evaluation and monitoring standards, and support reliable deployments and production quality checks.
Requirements
The role calls for experience with LLM observability and evaluation tools, AI platforms and agent frameworks, and cloud-native operations using Kubernetes, Helm, Kustomize, and GitOps. Relevant skills include monitoring platforms, Python, Java or Go, APIs, CI/CD, and security practices such as access control, secrets management, PII protection, and audit logging.
