Observability Engineer — AgentCore Telemetry

EPAM Systems; Portugal; Remote; EUR 60,000 - 100,000; Full time

Benefits offered by this job

Remote work

Career growth opportunities

Job summary

EPAM Systems is seeking an Observability Engineer — AgentCore Telemetry to own the observability stack for our cloud-native Enterprise Agent Development Platform, deployed across distributed AI agents in a fully remote role based in Portugal.

You will design, implement, and maintain tracing, metrics, and logging pipelines using OpenTelemetry and AWS services, ensuring health, performance, and compliance across agent runtimes and CI/CD workflows.

Qualifications

• 3+ years of observability engineering or telemetry design for distributed systems.
• Hands-on experience instrumenting Python services with OpenTelemetry.
• Experience configuring AWS CloudWatch and AWS X-Ray for distributed tracing.

Responsibilities

• Implement observability for distributed AI agent systems using ADOT and the OpenTelemetry SDK for Python.
• Design and maintain telemetry pipelines for metrics, traces, and structured logs across agent runtimes.
• Integrate AWS CloudWatch and AWS X-Ray for real-time monitoring and distributed tracing.
• Ensure proper trace-context propagation aligned with W3C Trace Context standards across agent flows.
• Instrument Python-based AI and agent frameworks (e.g., LangChain) for granular telemetry coverage.
• Define observability best practices and semantic conventions for agentic and LLM-based systems.
• Configure and manage ADOT collector for custom pipelines and data export to observability platforms.
• Collaborate with platform engineering, security, and DevOps to establish monitoring baselines and compliance.
• Provide guidance on observability strategies supporting CI/CD, scaling, and fault isolation.

Skills

OpenTelemetry

Python

AWS CloudWatch

AWS X-Ray

Trace Context

Telemetry Pipelines

Distributed Systems

Tools

ADOT Collector

OpenTelemetry SDK

LangChain

Job description

We're looking for an Observability Engineer — AgentCore Telemetry to join our team in Portugal in a fully remote working mode. In this role, you will own observability and telemetry for the Enterprise Agent Development Platform, a cloud-native ecosystem that enables teams to build, deploy, and monitor AI agents at scale. You will design and implement tracing, metrics, and logging solutions leveraging OpenTelemetry and AWS native services to ensure system health, performance optimization, and compliance with enterprise standards. This position combines deep expertise in instrumentation, distributed tracing, and integration of observability pipelines with cutting-edge agentic AI architecture.

Responsibilities

• Implement observability for distributed AI agent systems using AWS Distro for OpenTelemetry (ADOT) and the OpenTelemetry SDK for Python
• Design and maintain telemetry pipelines for metrics, traces, and structured logs across agent runtimes
• Integrate AWS CloudWatch and AWS X-Ray for real-time system monitoring and distributed tracing
• Ensure proper trace-context and baggage propagation aligned with W3C Trace Context standards across agent orchestration flows
• Instrument Python-based AI and agent frameworks, including LangChain or comparable runtime tools, for granular telemetry coverage
• Define observability best practices and integrate semantic conventions for agentic and LLM-based systems
• Configure and manage ADOT collector for custom pipelines and data export to enterprise observability platforms
• Collaborate with platform engineering, security, and DevOps teams to establish baselines for monitoring, alerting, and compliance
• Provide guidance on observability strategies supporting CI/CD, scaling, and fault isolation

Requirements

• 3+ years of experience in observability engineering or telemetry design for distributed systems
• Strong hands-on experience instrumenting Python services with OpenTelemetry
• Practical experience configuring AWS CloudWatch (logs, metrics) and AWS X-Ray for distributed tracing
• Familiarity with trace-context standards and end-to-end instrumentation strategies for microservices or event-driven architectures
• Ability to design and maintain scalable telemetry pipelines in a production-grade environment

Nice to have

• Exposure to LangGraph or Strands agent orchestration frameworks
• Familiarity with OpenTelemetry GenAI SIG semantic conventions for AI/LLM observability
• Experience with ADOT collector configuration and custom export setup
• Background in observability for multi-agent or generative AI systems

We offer

• Competitive compensation depending on experience and skills
• Variety of projects within one company
• Being a part of a project following engineering excellence standards
• Individual career path and professional growth opportunities
• Internal events and communities
• Flexible work hours