Observability & Evaluation Engineer – Agentic AI

2 days ago

Charlotte, North Carolina, United States ZealTech Full-time
We're Hiring: Observability & Evaluation Engineer – Agentic AI

Location:
Charlotte, NC (Onsite) # Hybrid # W2 only We are looking for an experienced Observability & Evaluation Engineer to support production-grade Agentic AI systems. This role focuses on building telemetry, tracing, dashboards, alerts, evaluation frameworks, and operational readiness processes for Tachyon agent releases. The ideal candidate will have strong Python engineering skills, hands-on observability experience, and a solid understanding of LLMs, AI agents, RAG, and AI evaluation methodologies. 🔹

Key Responsibilities
• Implement observability and telemetry for LLM-powered applications, AI agents, tools, and platform services.
• Build evaluation suites for agent behavior, prompt quality, response quality, retrieval performance, latency, reliability, and safety.
• Develop dashboards, metrics, traces, alerts, SLOs, and production monitoring reports.
• Collaborate with platform engineers and Product Owners to define monitoring requirements and evaluation metrics.
• Automate evidence collection for release readiness, operational reviews, and governance checkpoints.
• Create runbooks and support documentation for priority agent releases.
• Analyze production behavior and recommend improvements in reliability, performance, and AI quality. 🔹 Required Qualifications
• 7+ years of engineering experience in observability, monitoring, test automation, platform operations, or AI/ML systems.
• 5+ years of hands-on Python development experience.
• 5+ years of experience with dashboards, metrics, alerts, tracing, logs, SLOs, and production monitoring.
• 5+ years of experience or demonstrated expertise in LLM evaluation, prompt evaluation, RAG evaluation, or AI quality assessment.
• Experience working in Agile engineering teams and production support environments. 🔹 Required Technical Skills
• Python, telemetry, tracing, monitoring, dashboards, alerting, and SLOs.
• Evaluation frameworks, test automation, and production operations.
• Understanding of LLMs, AI agents, RAG, prompt performance, retrieval quality, latency, and reliability metrics.
• Observability tools and OpenTelemetry concepts. 🔹 Preferred Qualifications
• Experience with GenAI observability, AI evaluation tools, ML monitoring, or platform reliability engineering.
• Experience in regulated environments requiring evidence collection and readiness documentation.
• Familiarity with Kubernetes, cloud platforms, and CI/CD pipelines. 🔹 Expected Outcomes
• Production-ready observability dashboards and evaluation suites for priority agent releases.
• Clear release-readiness evidence, actionable alerts, SLOs, and runbooks.
• Improved quality, reliability, and trust in production Agentic AI systems.