Platform Reliability Engineer

In this role you make the platform visible and dependable. You'll build the OpenTelemetry instrumentation, observability integrations, tracing, SLOs, alerting, and cost monitoring for token and compute spendWhen an agent is slow, wrong or expensive, your work is how the team finds out and fixes it. This is a named-team engagement, so the person we propose is the person who startsInstrumentation: Build OpenTelemetry instrumentation standards for agents, tools and platform services, and make it easy for teams to adoptObservability Integration: Connect AgentCore Observability and CloudWatch with the client's existing observability tools (e.G., Datadog, Splunk, Grafana)Tracing: Set up end-to-end tracing across agent steps, model calls, tool calls and multi-agent handoffs so issues can be traced to their sourceSLOs and Alerting: Define SLOs for latency, availability and error rates, and build alerting that is useful and not noisyCost Monitoring: Track token usage and compute spend by team, agent and environment, with dashboards, budgets and alerts for unexpected spikesIncident Readiness: Write runbooks, support incident response and run post-incident reviews that lead to real fixesScripting and coding skills in Python, Go or TypeScriptClear communication and able to turn data into decisions for technical and non-technical audiencesExperience building cost visibility and FinOps reporting on AWS (Cost Explorer, CUR, tagging strategies)Experience with Amazon CloudWatch and at least one enterprise observability platform (Datadog, Splunk, Grafana, New Relic or similar)Hands-on experience with OpenTelemetry (SDKs, collectors, exporters) and distributed tracing6+ years in SRE, platform reliability or observability engineering, with strong hands-on AWS experienceExperience defining and running SLOs, error budgets and alerting strategiesExperience monitoring LLM or agent-based applications, including token usage, latency and quality signalsFamiliarity with LLM observability tools (e.G., Langfuse, Arize, LangSmith) or AgentCore ObservabilityPrior experience and connections in the Life Sciences industry is preferredYou have prior experience in consultingYou want to know what's happening in a system before a user tells youYou work well inside a client team and build trust quicklyYou treat cost as a reliability concern, not an afterthoughtYou build alerts people trust and dashboards people actually openExperience in pharma, life sciences or another regulated industryExperience with infrastructure as code (Terraform or AWS CDK) for monitoring resourcesYou stay calm in incidents and focus on learning afterward
#J-18808-Ljbffr