Enterprise AI Observability Engineer

Moring AI; Alpharetta (GA); In loco; USD 140.000 - 180.000; Tempo pieno

Descrizione del lavoro

Moring.ai seeks an AI Observability Engineer to own end-to-end observability for our AI platform in a production-like environment. You will implement OpenTelemetry across agents and services, stand up LangSmith, and ensure dashboards, cost tracking, and audits are reliable.

You will work with Kubernetes in enterprise contexts, integrate with customer environments, and help engineers, operations teams, and auditors understand system behavior and performance.

Competenze

• 6+ years in software or platform engineering with observability focus.
• Strong logs, traces, and metrics fundamentals across production systems.
• Deep OpenTelemetry experience: SDKs, collector, instrumentation libraries, and conventions.
• Experience building observability platforms for cloud-native systems (Kubernetes, Prometheus, Grafana, Jaeger/Tempo).

Mansioni

• Own the observability architecture for the AI platform end-to-end.
• Stand up LangSmith and integrate into client stack.
• Instrument the platform with OpenTelemetry across services and signals.
• Build and operate OTel pipelines and backends with redaction and policy controls.
• Create dashboards and alerts for cost, latency, token usage, and reliability.
• Collaborate with engineers, ops, and auditors to surface insights.

Conoscenze

OpenTelemetry

Python

Kubernetes

AWS

Observability

Formazione

Bachelor's degree in Computer Science

Strumenti

LangSmith

Langfuse

Arize Phoenix

Prometheus

Grafana

Descrizione del lavoro

Moring.ai seeks an AI Observability Engineer to own end-to-end observability for our AI platform in a production-like environment. You will implement OpenTelemetry across agents and services, stand up LangSmith, and ensure dashboards, cost tracking, and audits are reliable.

You will work with Kubernetes in enterprise contexts, integrate with customer environments, and help engineers, operations teams, and auditors understand system behavior and performance.