AI Platform Engineer: Observability & DevOps Lead

EY; McLean (VA); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Total Rewards package

Paid time off

Medical and dental coverage

Job summary

EY is seeking an AI Systems Engineer to own the delivery, model‑serving, routing, and observability layer of EY’s AI‑native platform. The role spans CI/CD, governance of AI assets, and cost‑aware, observable AI workloads across cloud, on‑prem, edge, and air‑gapped environments.

This distinct discipline sits at the intersection of DevOps, MLOps, FinOps, and observability and requires deep expertise in GPU inference and production‑grade model serving frameworks.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or related field.
• Hands‑on ownership of AI or high‑throughput services in production.
• Extensive experience with CI/CD/CV pipelines and GitOps tooling.
• Hands‑on experience with inference/model‑serving frameworks on GPU infrastructure.
• Strong observability experience across metrics, logs, traces, and OpenTelemetry.

Responsibilities

• Own DevOps and delivery for AI workloads, including CI/CD/CV pipelines and rollout.
• Oversee governance and discovery for AI assets and registries.
• Manage cost attribution, quotas, and per-tenant FinOps.
• Own the full observability stack: Prometheus, Grafana, Loki, Tempo/Jaeger.
• Automate GitOps delivery and ensure policy-compliant releases.

Skills

DevOps / MLOps

Observability

OpenTelemetry

GitOps

GPU inference

Model serving

APIs & gateways

FinOps / cost control

Cloud & edge

Regulatory/compliance

Education

Bachelor’s or Master’s in Computer Science or related field

Tools

Ray Serve

vLLM

Triton

NIM

Envoy

MLflow

Harbor

Trivy

Prometheus

Grafana

Loki

Tempo

OpenLineage

Kubecost/OpenCost

Job description

EY is seeking an AI Systems Engineer to own the delivery, model‑serving, routing, and observability layer of EY’s AI‑native platform. The role spans CI/CD, governance of AI assets, and cost‑aware, observable AI workloads across cloud, on‑prem, edge, and air‑gapped environments.

This distinct discipline sits at the intersection of DevOps, MLOps, FinOps, and observability and requires deep expertise in GPU inference and production‑grade model serving frameworks.