Lead Site Reliability Engineer

We are looking for a Lead Site Reliability Engineer to join our team building an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime. The initiative spans agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability, reducing agent development from months to days while enforcing consistent security, quality, and governance standards. Responsibilities Build consolidated cross-tenant dashboards covering agent health, cost, and estate overview Develop governed cost and token usage metrics for GenAI and compute workloads Derive governed aggregate metrics from raw telemetry while preserving lineage rather than creating raw copies Establish clear segregation between technical and business observability through proper derivation, replication, and linkage practices Maintain metric facet hygiene by enforcing consistent, low-cardinality dimensions Translate raw telemetry into governed, reusable aggregate metrics across the agent estate Design and maintain NRQL queries to support dashboard functionality and reporting needs Partner with engineering teams to standardize observability practices across the agent platform Requirements 3+ years of experience in observability engineering Hands-on experience building cost and token usage observability for GenAI or agentic workloads in production, such as New Relic dashboards/NRQL for agent estate health, governed cost-metric derivation from raw agent telemetry, or gen_ai.* semantic conventions Expertise in dashboard building and NRQL queries within New Relic Proficiency in dashboard and cost-metric implementation on New Relic or equivalent SaaS observability platforms Skills in translating raw telemetry into governed, reusable aggregate metrics Understanding of technical vs business observability segregation, including derivation, replication, and linkage Nice to have Familiarity with New Relic Metric API / Firehose ingestion Knowledge of AWS cost allocation, including Cost Explorer, tagging, and per-account attribution Familiarity with OpenTelemetry GenAI semantic conventions (gen_ai., pmi.agent.) Experience feeding a downstream BI/analytics data product