We are seeking a Senior Site Reliability Engineer to contribute to our Enterprise Agent Development Platform which is a cloud-native ecosystem facilitating the orchestration deployment and monitoring of AI agents at scale. This role involves standardizing agent development utilizing tools like LangGraph and Strands Agents on AWS AgentCore Runtime while focusing on agent framework design runtime architecture and marketplace integration. The engineer will play a crucial role in reducing agent development timelines and ensuring adherence to security quality and governance standards. Responsibilities include building monitoring systems designing dashboards implementing metrics emission and collaborating with engineering teams to enforce consistent practices across the agent platform. The ideal candidate should possess at least 3 years of experience in observability engineering with hands-on expertise in behavioral monitoring for AI agents while being proficient in New Relic and Python. A solid understanding of observability practices and domain segregation between technical monitoring and audit evidence is essential for success in this role.
