AI Observability Engineer: Build Telemetry & Dashboards

Galent; Plano (TX); On-site; USD 90,000 - 130,000; Full time

Job summary

Galent in Plano, TX seeks an experienced AI Observability Engineer to design, implement, and manage enterprise-scale observability for ML, GenAI, and LLM platforms. You will establish end-to-end visibility into AI workloads, monitor model performance, latency, cost, data quality, drift, and user experience.

The role requires building dashboards with Grafana/Tableau, creating metrics with Prometheus/PromQL, and collaborating with AI/ML, Platform, and SRE teams to improve production reliability.

Qualifications

• Proven years of experience in observability, monitoring, analytics, or telemetry engineering.
• Proven years of experience creating operational dashboards and visualizations.
• Experience supporting production-scale applications in cloud or distributed environments.

Responsibilities

• Build and maintain observability solutions for AI/ML applications and platform services.
• Develop dashboards and alerts using Grafana and Tableau.
• Monitor AI service health, latency, throughput, error rates, and reliability metrics.
• Create and maintain metrics using Prometheus and PromQL.
• Analyze operational and time-series data to identify trends and performance issues.
• Define and monitor SLIs, SLOs, and service health indicators.
• Partner with AI/ML, Platform, and SRE teams to improve production reliability.
• Support incident troubleshooting and root cause analysis

Skills

Observability engineering

Dashboard development

Telemetry analysis

Tools

Prometheus

Grafana

Thanos

OpenTelemetry

Jira

Job description

Galent in Plano, TX seeks an experienced AI Observability Engineer to design, implement, and manage enterprise-scale observability for ML, GenAI, and LLM platforms. You will establish end-to-end visibility into AI workloads, monitor model performance, latency, cost, data quality, drift, and user experience.

The role requires building dashboards with Grafana/Tableau, creating metrics with Prometheus/PromQL, and collaborating with AI/ML, Platform, and SRE teams to improve production reliability.