Remote Observability Engineer – AI Agent Telemetry

EPAM Systems, Inc.; Portugal; Remote; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Flexible work hours

Competitive compensation

Job summary

EPAM Systems, Inc. is seeking an Observability Engineer — AgentCore Telemetry to own observability and telemetry for a cloud-native enterprise AI platform.

You will design tracing, metrics, and logging solutions using OpenTelemetry and AWS services to ensure health, performance, and enterprise compliance. You will instrument Python-based AI runtimes, align with W3C trace contexts, and build scalable telemetry pipelines.

Qualifications

• 3+ years of observability or telemetry design for distributed systems.
• Hands-on experience instrumenting Python services with OpenTelemetry.
• Configuring AWS CloudWatch (logs, metrics) and AWS X-Ray for distributed tracing.
• Familiarity with trace-context standards and end-to-end instrumentation strategies.
• Nice to have LangGraph or Strands orchestration frameworks.
• Familiarity with OpenTelemetry GenAI SIG semantic conventions for AI/LLM observability.

Responsibilities

• Implement observability for distributed AI agent systems using ADOT and OpenTelemetry SDK for Python.
• Design and maintain telemetry pipelines for metrics, traces, and logs across agent runtimes.
• Integrate AWS CloudWatch and AWS X-Ray for real-time monitoring and tracing.
• Ensure proper trace-context propagation across agent orchestration flows.
• Instrument Python-based AI frameworks for granular telemetry coverage.
• Configure ADOT collector for custom pipelines and data export to observability platforms.
• Collaborate with platform engineering, security, and DevOps to establish monitoring baselines.
• Provide guidance on observability strategies for CI/CD, scaling, and fault isolation.

Skills

OpenTelemetry

Python

Distributed tracing

Trace context

AWS CloudWatch

AWS X-Ray

Instrumentation

Tools

ADOT collector

OpenTelemetry SDK

LangGraph

Strands

Job description

EPAM Systems, Inc. is seeking an Observability Engineer — AgentCore Telemetry to own observability and telemetry for a cloud-native enterprise AI platform.

You will design tracing, metrics, and logging solutions using OpenTelemetry and AWS services to ensure health, performance, and enterprise compliance. You will instrument Python-based AI runtimes, align with W3C trace contexts, and build scalable telemetry pipelines.