AI Observability Engineer (Azure)

Location: Amsterdam, Netherlands

Company

Nebius is building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment.

What you will do

• Stand up and operate LLM and agent monitoring using Langfuse.
• Capture traces, latency, token usage, cost, quality scores, and safety signals.
• Develop lightweight internal tooling and exporters in Python.
• Design and maintain Grafana dashboards, Prometheus metrics, and the Azure observability stack.
• Manage observability infrastructure using Terraform IaC and CI/CD pipelines.
• Support incident investigation and root-cause analysis.

Requirements

• 5–8 years of experience in observability, SRE, platform engineering, or DevOps.
• Strong experience with Azure Monitor, Application Insights, Log Analytics, and Managed Grafana.
• Hands-on experience with Langfuse, Grafana, and Prometheus.
• Python skills for instrumentation, exporters, and automation.
• Experience with Terraform and CI/CD.
• English: Intermediate or higher required.
• Must be authorized to work in the country in which you apply.

Nice to have

• Proficiency in PromQL and Kusto Query Language.
• Experience with OpenTelemetry and GenAI semantic conventions.
• Knowledge of LLM evaluation frameworks and AI FinOps.
• AKS and Kubernetes observability experience.

Culture & Benefits

• Competitive compensation and career growth opportunities.
• Flexibility, ownership, and a collaborative, innovative culture.
• Opportunity to work on impactful AI projects within an international environment.
• Access to a talented team of engineers in a fast-moving environment.