Senior AWS Observability Engineer

Make AI platforms visible and dependable through OpenTelemetry, distributed tracing, and AWS observability engineering. This consulting engagement requires hands-on reliability expertise.

As a Platform Reliability Engineer, you will build instrumentation and observability for agents, tools, and platform services. You will connect AgentCore Observability and CloudWatch with Datadog, Splunk, Grafana, or similar platforms. Your work will expose latency, errors, quality signals, token usage, and compute spend.

Key Responsibilities:

• Build OpenTelemetry instrumentation standards for agents and platform services
• Connect AgentCore Observability and CloudWatch with existing tools
• Trace agent steps, model calls, tools, and handoffs
• Define SLOs and useful alerting for reliability signals
• Track token usage and compute spend through dashboards

Requirements:

• Six-plus years in SRE, platform reliability, or observability
• Strong hands-on AWS experience with Python, Go, or TypeScript
• OpenTelemetry, distributed tracing, and CloudWatch experience
• FinOps reporting using Cost Explorer, CUR, and tagging
• Experience monitoring LLM or agent-based applications

Apply platform reliability, AWS, OpenTelemetry, and tracing expertise to dependable agent systems and actionable observability.