Senior AI Systems Engineer — DevOps, Observability

EY; Atlanta (GA); Hybrid; USD 107,000 - 177,000; Full time

Job summary

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY’s AI-native platform. You will oversee CI/CD/CV pipelines, governance of AI assets, cost attribution, and deep observability across cloud, on-prem, edge, and air-gapped environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring hands-on leadership in automated delivery, GPU inference, and regulated workloads.

Qualifications

• Experience delivering AI workloads with CI/CD/CV pipelines and GitOps tooling.
• Proven ability to operate model-serving/inference at production scale on GPUs.
• Strong observability skills across metrics, logs, and traces with OpenTelemetry.
• Familiarity with model/artifact registries, CVE scanning, license/lineage tracking.

Responsibilities

• Build and operate CI/CD/CV pipelines for AI services and runtime components.
• Own governance and discovery for AI assets and registries (Harbor, MLflow).
• Manage resource/cost controls and quota enforcement for multi-tenant AI workloads.
• Own full observability stack: metrics, logs, traces, dashboards.
• Automate GitOps-based delivery with quality and cost gates.
• Drive deployment decisions using telemetry and cost signals.

Skills

CI/CD pipelines

GitOps tooling

Observability

OpenTelemetry

GPU inference

FinOps

Model governance

LangSmith

Langfuse

Ray Serve

Triton

Prometheus

Grafana

Jaeger

Harbor

MLflow

Trivy

OpenLineage

Education

Bachelor’s or Master’s in CS

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Envoy

Kubecost

OpenCost

HuggingFace

NGC

MLflow

Job description

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY’s AI-native platform. You will oversee CI/CD/CV pipelines, governance of AI assets, cost attribution, and deep observability across cloud, on-prem, edge, and air-gapped environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring hands-on leadership in automated delivery, GPU inference, and regulated workloads.