AI Observability Engineer - GenAI & Agentic AI

GL Global Limited; Charlotte (NC); On-site; USD 110,000 - 145,000; Full time

Job summary

GL Global Limited is seeking an AI Observability Engineer to support the development and production of next‑generation GenAI and Agentic AI systems. The role focuses on building telemetry, monitoring, dashboards, alerts, tracing and SLOs for AI/LLM applications and agents.

Ideal candidates have 4+ years in observability, SRE, MLOps or related fields, and hands‑on experience with metrics, logs, and AI evaluation methods. Production support experience is important for this role.

Qualifications

• 4+ years' engineering experience across observability, monitoring, platform engineering, SRE, AI/ML or test automation.
• Experience with metrics, logs, traces, dashboards, alerting and SLOs.
• Understanding of LLMs, AI agents, RAG or AI evaluation.

Responsibilities

• Build telemetry, monitoring, dashboards, alerts, tracing and SLOs for AI/LLM applications and agents.
• Develop LLM and AI evaluation frameworks covering response quality, prompts, RAG, latency, reliability and safety.
• Analyse production behaviour and identify improvements to AI quality, performance and reliability.
• Automate production readiness, reporting and governance processes.
• Create runbooks and operational documentation for AI releases.
• Work closely with Engineering and Product teams to define monitoring and evaluation requirements.

Skills

Observability

SRE

MLOps

Platform Engineering

Test Automation

Job description

AI Observability Engineer - GenAI & Agentic AI

We’re looking for an experienced AI Observability Engineer to support the development and production of next-generation GenAI and Agentic AI systems.

This is a great opportunity for someone with a background in Observability, SRE, MLOps, Platform Engineering, AI/ML or Test Automation who wants to work on cutting-edge AI technology.

Key Responsibilities:

• Build telemetry, monitoring, dashboards, alerts, tracing and SLOs for AI/LLM applications and agents
• Develop LLM and AI evaluation frameworks covering response quality, prompts, RAG, latency, reliability and safety
• Analyse production behaviour and identify improvements to AI quality, performance and reliability
• Automate production readiness, reporting and governance processes
• Create runbooks and operational documentation for AI releases
• Work closely with Engineering and Product teams to define monitoring and evaluation requirements

Experience:

• 4+ years' engineering experience across observability, monitoring, platform engineering, SRE, AI/ML or test automation
• Experience with metrics, logs, traces, dashboards, alerting and SLOs
• Understanding of LLMs, AI agents, RAG or AI evaluation
• Experience supporting production systems

If you're an AI Observability Engineer, GenAI Engineer, SRE, MLOps Engineer, Platform Engineer or AI/ML Engineer looking to work on production Agentic AI systems, we'd love to hear from you.