AI Observability Engineer

2T Consulting

Chandler, AZ

Posted On: Nov 18, 2026

Posted On: Nov 18, 2026

Job Overview

Job Type

Full-time

Experience

5 - 10 Years

Salary

Depends on Experience

Work Arrangement

On-Site

Travel Requirement

0%

Required Skills

  • Tableau
  • Grafana
  • Prometheus
  • PromQL
  • Visualization
  • Linux
Job Description

Our client is seeking an experienced AI Observability Engineer with strong expertise in data analysis, visualization, monitoring, and dashboard development. The ideal candidate will have hands-on experience with Grafana, Tableau, Prometheus, PromQL, and time-series data.

The candidate will design, implement, and maintain observability solutions for AI/ML and Large Language Model (LLM) applications, ensuring visibility into model performance, reliability, latency, cost, data quality, and user experience.

Required Technical Skills
  • Minimum 5 years of experience in data visualization and dashboard development.
  • Strong hands-on experience with Grafana and Tableau.
  • Experience with Prometheus, PromQL, and time-series monitoring.
  • Strong knowledge of Linux and SQL.
  • Expertise in creating interactive dashboards, visualizations, graphs, and performance reports.
  • Experience with application monitoring, telemetry, and observability solutions.
  • Understanding of AI/ML application monitoring and performance metrics.
Roles & Responsibilities
  • Design, develop, and maintain Grafana and Tableau dashboards for application and AI/ML observability.
  • Implement monitoring solutions using Prometheus and PromQL.
  • Build telemetry dashboards to track model latency, token usage, throughput, error rates, and service reliability.
  • Monitor AI/LLM application performance, data quality, model drift, safety, and operational costs.
  • Define and monitor Service Level Objectives (SLOs) and performance indicators.
  • Analyze time-series data and identify performance bottlenecks and operational issues.
  • Evaluate and integrate observability tools for metrics, logs, traces, and model telemetry.
  • Collaborate with ML engineers and platform teams to improve production observability.
  • Develop self-service dashboards and reporting solutions for engineering teams.
Preferred Skills
  • Thanos monitoring stack.
  • Python programming.
  • Bash scripting.
  • Agile methodologies and Jira.
  • Experience with AI/ML and LLM monitoring frameworks.
Ideal Candidate Profile
  • Strong analytical and problem-solving skills.
  • Excellent expertise in data visualization and dashboard development.
  • Hands-on experience with Grafana, Prometheus, Tableau, and observability tools.
  • Understanding of AI/ML application performance monitoring.
  • Ability to translate complex telemetry data into actionable insights.

Job ID: 2C322890


Posted By

Shayne sha

Sr. Recruiter