Observability Engineer - AgentCore Telemetry

Intellias; Portugal; Presencial; EUR 60 000 - 90 000; Tempo integral

Resumo da oferta

Intellia is seeking an Observability Engineer to build and evolve telemetry capabilities for AI platforms and agent-based systems on AWS. You will design end-to-end tracing, instrument Python services, and implement dashboards for operational visibility.

The role involves collaborating with AI Platform Engineers and DevOps to establish observability standards, improve reliability, and support production-grade monitoring across distributed services.

Qualificações

• 4+ years of observability engineering experience.
• OpenTelemetry instrumentation of Python services.
• AWS CloudWatch and X-Ray integration experience.

Responsabilidades

• Design observability solutions for AI platforms and distributed apps.
• Instrument Python services using OpenTelemetry and ADOT.
• Develop and maintain tracing with AWS X-Ray and OpenTelemetry.
• Configure telemetry collection, propagation, and export pipelines in AWS environments.
• Create CloudWatch dashboards, metrics, logs, and alerts for operations.
• Establish monitoring standards for AI agents and workflows.
• Ensure proper W3C Trace Context and baggage propagation across systems.
• Instrument LangChain-based applications to capture traces and metrics.
• Collaborate with AI engineers and platform teams to optimize performance and reliability.

Conhecimentos

ADOT

OpenTelemetry

CloudWatch

X-Ray

LangChain

Trace Context

Ferramentas

Python

Descrição da oferta de emprego

Permanent employment contract in Portugal

Observability Engineer - AgentCore Telemetry

We are looking for an Observability Engineer - AgentCore Telemetry to build and evolve observability capabilities for enterprise AI platforms and agent-based systems running on AWS. In this role, you will design telemetry solutions, implement end-to-end tracing strategies, and provide deep operational visibility into AI workflows, agent interactions, and distributed services. You will work closely with AI Platform Engineers, DevOps teams, and application developers to establish observability standards, improve reliability, and support production-grade monitoring of agent ecosystems.

Project Overview:

Our customer is a multinational corporation with more than a century of history and offices in over 180 countries. Their most ambitious goal at the time is to introduce a range of Reduced-Risk Products (RRPs). The target audience is more than 1 billion consumers around the globe. IT platform hosts 700+ applications.

Intellia's mission is to help the client with the engineering of a comprehensive software ecosystem for a game-changing IoT product on the margin of innovative consumer experience and cutting-edge technology. Our teams are involved in the engineering of core platform components for best-in-class eCommerce, Digital Marketing and IoT solutions. As an Engineer, you will become a part of Core Architecture Team and be responsible for the architecture, implementation of best practices in our Digital Engineering Enterprise Platform.

The Platform is a set of services and internet applications that accelerate the development and delivery of software applications by taking care of common SDLC challenges. The Platform provides access and consumption for engineering teams to a set of services, technologies, practices for their development and for operating their application, ensuring a set of compliance and best practices.

Skills:

• AWS Distro for OpenTelemetry (ADOT)
• OpenTelemetry SDK (Python)
• AWS CloudWatch (Metrics, Logs, Structured Logs)
• AWS X-Ray (distributed tracing)
• LangChain instrumentation
• W3C Trace Context and Baggage propagation

Experience:

• 4+ years of observability engineering
• OpenTelemetry instrumentation of Python services
• AWS CloudWatch and X-Ray integration

Nice to have:

• LangGraph or Strands agent framework
• OpenTelemetry GenAI SIG semantic conventions
• ADOT collector configuration and export pipeline setup

Responsibilities:

• Design and implement observability solutions for AI platforms, agent-based systems, and distributed cloud-native applications.
• Instrument Python services using OpenTelemetry SDK and AWS Distro for OpenTelemetry (ADOT).
• Develop and maintain distributed tracing solutions using AWS X-Ray and OpenTelemetry.
• Configure telemetry collection, propagation, and export pipelines across AWS environments.
• Implement and maintain CloudWatch dashboards, metrics, logs, and alerting strategies for operational visibility and troubleshooting.
• Establish monitoring standards for AI agents, tool invocations, workflow execution, and service-to-service communication.
• Integrate observability capabilities with AWS AgentCore Observability and related platform services.
• Ensure proper W3C Trace Context and Baggage propagation across applications, APIs, and agent workflows.
• Instrument LangChain-based applications and AI services to capture traces, metrics, and execution insights.
• Partner with AI engineers and platform teams to identify performance bottlenecks, reliability issues, and optimization opportunities.
• Build structured logging and telemetry standards that support debugging, root-cause analysis, and operational governance.
• Contribute to observability best practices, platform standards, and engineering guidelines for AI and cloud-native systems.