SSE- AgentOps Professional

About the role

ClOUDSUFI is hiring an AgentOps Engineer to own the runtime, infrastructure, and operational monitoring for an AI agent testing platform deployed for an enterprise client. You will deploy and instrument agents for testing, set up observability and continuous evaluation on live traffic, and manage the cloud infrastructure the platform runs on.

Responsibilities

- Deploy and instrument AI agents for testing and monitoring.

- Set up observability - traces, logs, and metrics - and continuous evaluation on production traffic.

- Build drift detection and alerting so quality regressions are caught early.

- Own the cloud infrastructure and CI/CD automation supporting the platform.

- Manage environments, access, and operational reliability.

Required qualifications

- 5-6+ years in DevOps, MLOps, or platform engineering.

- Strong Google Cloud experience (Cloud Run, Cloud Build, Pub/Sub, Cloud Logging and Monitoring, IAM) or equivalent cloud platform.

- Experience with CI/CD automation and infrastructure as code.

- Familiarity with deploying LLM or AI agent workloads.

Preferred qualifications

- Experience with OpenTelemetry and AI/agent observability.

- Exposure to Vertex AI, Gemini Enterprise Agent Platform, or ADK.