Observability Engineer - AI & Agent 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

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.