AI Platform Engineer: DevOps, Observability & FinOps

EY; Columbus (OH); On-site; USD 107,000 - 177,000; Full time

Job summary

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability for EY’s AI-native platform. You will shape how AI services are built, deployed, and governed across cloud, on‑prem, edge, and air‑gapped environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, delivering repeatable, economical workloads with policy‑driven gates and strong cost visibility.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on AI workloads.
• Hands-on CI/CD/CV pipelines and GitOps tooling for automated build, test, release, rollback.
• Operations experience with inference/model-serving frameworks on GPU infrastructure.
• Strong observability stack experience: Prometheus, Grafana, Loki, OpenTelemetry.
• Familiarity with model/artifact registries, registry security, and license/lineage tracking.
• Ability to define ownership boundaries and per-tenant cost contracts.

Responsibilities

• Own CI/CD/CV pipelines and deployment for AI workloads across environments.
• Govern AI assets catalogs, registries, and license lineage.
• Manage resource quotas and cost attribution per tenant and workload.
• Own the observability stack: metrics, logs, traces, dashboards, and SLA alerts.
• Oversee OpenTelemetry collection and multi-tenant signal routing.
• Automate GitOps delivery with quality and cost gates.
• Drive end-to-end deployment decisions using telemetry and cost signals.
• Ensure governance and compliance in regulated delivery contexts.

Skills

DevOps & MLOps

Observability

Cost governance

Communication

Cloud/Edge awareness

Education

Bachelor's or Master's in CS or related

Tools

Ray Serve

vLLM / Triton / NIM

Prometheus

Grafana

Loki

Tempo / Jaeger

OpenTelemetry

Envoy

Harbor

MLflow

Trivy / SBOM

Kubecost / OpenCost

ArgoCD / Helm / GitHub Actions

Job description

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability for EY’s AI-native platform. You will shape how AI services are built, deployed, and governed across cloud, on‑prem, edge, and air‑gapped environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, delivering repeatable, economical workloads with policy‑driven gates and strong cost visibility.