Remote Observability Engineer — AI Agent Telemetry

EPAM Systems Inc; United States; Remote; USD 69,000 - 104,000; Full time

Job summary

Unknown is seeking an Observability Engineer — AgentCore Telemetry to own observability and telemetry for a cloud-native AI agent platform. You will design tracing, metrics, and logs using OpenTelemetry and AWS services to ensure health, performance, and compliance.

You'll implement ADOT-based telemetry pipelines, integrate CloudWatch and X-Ray, and collaborate with platform engineering and DevOps to set baselines for monitoring and CI/CD readiness.

Qualifications

• 3+ years in observability or telemetry design for distributed systems.
• Experience instrumenting Python services with OpenTelemetry.
• Experience configuring AWS CloudWatch and AWS X-Ray for distributed tracing.
• Familiarity with trace-context standards and end-to-end instrumentation.

Responsibilities

• Implement observability for distributed AI agent systems using ADOT and the OpenTelemetry Python SDK.
• Design telemetry pipelines for metrics, traces, and logs across agent runtimes.
• Integrate AWS CloudWatch and AWS X-Ray for real-time monitoring and distributed tracing.
• Ensure proper trace-context propagation across orchestration flows.
• Instrument Python-based AI frameworks for telemetry coverage.
• Define observability best practices and semantic conventions for AI/LLM systems.
• Configure ADOT collector for custom pipelines and data export.

Skills

OpenTelemetry

Python instrumentation

AWS CloudWatch

AWS X-Ray

Distributed tracing

Telemetry pipelines

Trace context

OpenTelemetry SDK

Tools

ADOT collector

LangGraph

Strands

LangChain

Job description

Unknown is seeking an Observability Engineer — AgentCore Telemetry to own observability and telemetry for a cloud-native AI agent platform. You will design tracing, metrics, and logs using OpenTelemetry and AWS services to ensure health, performance, and compliance.

You'll implement ADOT-based telemetry pipelines, integrate CloudWatch and X-Ray, and collaborate with platform engineering and DevOps to set baselines for monitoring and CI/CD readiness.