AI Observability Engineer: Azure Metrics & Tracing Lead

Nebius B.V.; Amsterdam; On-site; EUR 70,000 - 110,000; Full time

Job summary

Nebius is building a high-performance AI cloud platform and seeks an AI Observability Engineer to own the observability backbone—from LLM and agent tracing to platform metrics—so the Azure AI platform is visible, measurable, reliable, and self-service.

You will stand up monitoring with Langfuse, capture traces, latency, token usage, cost, quality scores, and AI metrics, and design Grafana dashboards while owning Terraform IaC and CI/CD for observability tooling.

Qualifications

• 5–8 years in observability, SRE, or cloud/platform engineering.
• Strong experience with Azure Monitor, Application Insights, Log Analytics, and Managed Grafana.
• Hands-on with Langfuse, Grafana, and Prometheus.
• Experience with Terraform and CI/CD.
• Python skills for instrumentation and automation.
• Familiarity with ML workloads and AI metrics.
• English at intermediate or higher.

Responsibilities

• Stand up and operate LLM and agent monitoring with Langfuse.
• Capture traces, latency, token usage, cost, quality scores, and AI metrics.
• Build lightweight internal tooling and exporters in Python.
• Design and maintain Grafana dashboards, Prometheus metrics, and Azure observability stack.
• Instrument platform and AI workloads for health, usage, cost, and SLA reporting.
• Feed telemetry and operational insights into the Platform Engineering backlog.
• Own Terraform IaC and CI/CD for observability tooling.
• Support incident investigation and root-cause analysis.

Skills

English (intermediate)

Tools

Azure Monitor

Application Insights

Log Analytics

Managed Grafana

Langfuse

Grafana

Prometheus

Terraform

CI/CD

Python

Kusto Query Language

PromQL

Job description

Nebius is building a high-performance AI cloud platform and seeks an AI Observability Engineer to own the observability backbone—from LLM and agent tracing to platform metrics—so the Azure AI platform is visible, measurable, reliable, and self-service.

You will stand up monitoring with Langfuse, capture traces, latency, token usage, cost, quality scores, and AI metrics, and design Grafana dashboards while owning Terraform IaC and CI/CD for observability tooling.