AI Observability Engineer — Telemetry & Dashboards

LTM; West Virginia; On-site; USD 120,000 - 190,000; Full time

Benefits offered by this job

Comprehensive Medical Plan

Disability Coverage

401(k) Plan with Company match

Life Insurance

Vacation Time & Paid Holidays

Paid Paternity/Maternity Leave

Job summary

LTIMindtree is seeking an AI Observability Engineer to design and build telemetry and dashboards across AI models and endpoints. You will integrate metrics, logs, and traces, and deliver self-service visualizations to help teams monitor health and reliability of AI systems.

The role emphasizes collaboration with ML engineers and platform teams to ensure production-ready observability and actionable insights from time-series data.

Qualifications

• At least 5 years of experience creating data visualizations and telemetry dashboards.
• Hands-on experience with Tableau and Grafana dashboard development.
• Experience with Prometheus, PromQL, and the Thanos monitoring stack.

Responsibilities

• Evaluate, integrate, or build observability tools across metrics, logs, traces, and model telemetry.
• Develop telemetry for AI models and endpoints, including latency, token throughput, error rates, and SLOs.
• Create self-service dashboards that enable teams to monitor the health, performance, and reliability of AI systems.
• Analyse time-series and operational data to identify trends, anomalies, and areas for improvement.
• Partner with ML engineers and platform teams to enable production-ready AI systems with clear visualizations.

Skills

Data visualization

Telemetry dashboards

Time-series analysis

Dashboard design

Tools

Prometheus

Grafana

Tableau

Thanos

Jira

SQL

Linux

Job description

LTIMindtree is seeking an AI Observability Engineer to design and build telemetry and dashboards across AI models and endpoints. You will integrate metrics, logs, and traces, and deliver self-service visualizations to help teams monitor health and reliability of AI systems.

The role emphasizes collaboration with ML engineers and platform teams to ensure production-ready observability and actionable insights from time-series data.