site reliability engineer for an AI agent platform

The team is 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, reducing development time while enforcing consistent security, quality, and governance standards.

• Build behavioral monitoring and auditability signal views across the agent estate
• Develop behavioral dashboards and alert conditions using New Relic and NRQL
• Design behavioral monitoring signals for anomaly detection, drift, safety signals, and policy denials
• Create auditability views that surface governance evidence for stakeholders
• Maintain segregation between technical monitoring (CloudWatch/New Relic) and audit evidence (dedicated evidence/SIEM stores)
• Validate alerts and verify dashboard data accuracy across the platform
• Implement metrics emission and validation using Python
• Partner with engineering teams to align behavioral monitoring with agent governance requirements

• At least 3 years of experience in observability engineering
• Hands-on experience building behavioral monitoring or auditability signals for AI agents in production, such as anomaly/drift detection on agent telemetry, surfacing Cedar/policy-denial events as monitoring inputs, or audit-evidence dashboards for agent governance
• Experience with behavioral and anomaly monitoring, including alert tuning on production telemetry
• Background working in environments with formal audit and compliance evidence requirements
• Proficiency in New Relic and NRQL for behavioral dashboards and alert conditions
• Python skills for metrics emission and validation

• Условий в вакансии нет