We are seeking a Lead Site Reliability Engineer to join our team in building a production-grade cloud-native ecosystem for designing orchestrating deploying and observing AI agents at scale. This role involves working with LangGraph and Strands Agents within the AWS AgentCore Runtime to standardize agent development. The successful candidate will be responsible for creating consolidated dashboards focused on agent health cost and estate while also developing metrics for cost and token usage related to GenAI and compute workloads. Establishing strong segregation between technical and business observability is crucial as well as maintaining metric hygiene by ensuring consistent low-cardinality dimensions. The role demands translating raw telemetry into governed aggregate metrics optimizing dashboard functionality and partnering with engineering teams to enforce observability practices throughout the platform.
