AI Observability Engineer

Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure.

Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI.

Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.

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

• Stand up and operate LLM and agent monitoring with Langfuse.

• Capture traces, latency, token usage, cost, quality scores, prompt and model-version analytics, and safety signals.

• Build lightweight internal tooling and exporters in Python.

• Design and maintain Grafana dashboards, Prometheus metrics, and the 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.

• 5–8 years of experience in observability, SRE, platform engineering, DevOps, or cloud engineering.

• Strong experience with Azure Monitor, Application Insights, Log Analytics, and Managed Grafana.

• Hands-on experience with Langfuse, Grafana, and Prometheus.

• Experience with Terraform and CI/CD.

• Python skills for instrumentation, exporters, and automation.

• Familiarity with ML workloads and AI-specific metrics.

• Knowledge of logs, metrics, traces, dashboards, alerting, SLIs, and SLOs.

• Intermediate or higher English.

• PromQL and Kusto Query Language.

• OpenTelemetry, including GenAI semantic conventions.

• LLM evaluation frameworks.

• AI cost dashboards and FinOps.

• Alerting, on-call, and incident management tooling.

• AKS and Kubernetes observability.

• Competitive compensation

• Career growth and learning