Job Summary
NA
Key Responsibilities
AI Agent Ops Engineer
• Accountable for the complete setup, management, and automation of the agent operating environment on Google Cloud Platform or hybrid, on-site environments.
• Particularly terraforms the GCP or hybrid cloud environment, to provision and manage all resources in a safe and compliant way that scales and can be easily re-used.
• Design and implement robust CI/CD pipelines and deployment patterns to ensure the smooth and reliable release of AI agents / Agent Systems.
• Establish and manage comprehensive monitoring, logging, and alerting aligned to centrally directed observability efforts on the way to support performance measurements and guarantee operational stability and safety.
Skill Requirements
Experience: 5-7+ years as a Platform Engineer, DevOps Engineer, or Cloud Engineer, with at least the last 2 years focused on managing complex GCP environments.
Proven Track Record: Demonstrable success in building and automating scalable, secure cloud infrastructure for production systems.
Key Skills:
Expert, 100% hands-on Google Cloud Platform (GCP) engineering know-how.
Deep expertise in Infrastructure as Code, specifically terraforming in GCP and alike (hybrid)cloud env.
Strong knowledge of modern CI/CD practices and deployment patterns for cloud-native applications.
Proven experience in setting up and managing observability tools (monitoring, logging, tracing).
Other Requirements
Experience: 5-7+ years as a Platform Engineer, DevOps Engineer, or Cloud Engineer, with at least the last 2 years focused on managing complex GCP environments.