Observability Engineer

Job Description Observability expert in Tableau, Grafana, Prometheus, Thanos. We are seeking an AI observability professional to design, implement and scale production-grade observability for ML/LLM applications covering model performance, data quality/drift, safety compliance, cost, latency, reliability (SLOs) and user experience. Responsibilities Evaluate, integrate, or build observability tooling (metrics, logs, traces + model telemetry). Partner closely with ML engineers and platform teams to enable trustworthy AI systems in production. Build telemetry for models—including latency, token, throughput, error rates, and SLOs for AI endpoints. Create self‑service dashboards. Required Skills Strong data analysis and visualization skills. Experience in Grafana dashboard creation and the Tableau, Grafana, Prometheus, Thanos stack. Knowledge of SQL, time‑series data, PromQL, Linux and various visualization graph types.

Qualifications Bachelor of Computer Science Salary Range $100,000–$120,000 per year #J-18808-Ljbffr