AI Systems Engineer: DevOps, Delivery & Observability

EY; Southfield (MI); On-site; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid/Remote work flexibility

Medical and dental coverage

401(k) plan with company match

Job summary

EY is seeking an AI Systems Engineer to own delivery, model serving, routing, and observability for our AI-native platform. You’ll work across cloud, on‑prem, edge, and air‑gapped environments with a focus on cost, governance, and telemetry.

The role blends DevOps, MLOps, FinOps, and observability, requiring 8+ years in related roles and hands‑on leadership of AI infrastructure at production scale.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with production ownership of AI workloads.
• Hands‑on DevOps experience: CI/CD/CV pipelines and GitOps tooling for automated build, test, release and rollback.
• Experience with inference/model‑serving frameworks on GPU infrastructure.
• Strong observability experience: Prometheus, Grafana, Loki, Tempo/Jaeger and OpenTelemetry.
• Familiarity with API gateways (Envoy) and request routing, including streaming responses.
• Experience with FinOps tooling and cost attribution for multi‑tenant workloads.
• Knowledge of model/artifact registries and supply‑chain scanning and governance.

Responsibilities

• Supports AI workload delivery with CI/CD/CV pipelines and automated release into diverse environments.
• Own governance and discovery for AI assets and registries, including MLflow and Harbor/registries.
• Manage resource costs, quotas, and attribution per tenant and engagement.
• Own the full observability stack: metrics, logs, traces, and dashboards for AI workloads.
• Automate GitOps delivery and embed policy checks into pipelines.
• Drive deployment decisions with telemetry signals and support automated rollbacks.

Skills

CI/CD pipelines

GitOps

Observability

Cloud & on‑prem

Cost optimization

Education

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

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Tempo

Jaeger

OpenTelemetry

Envoy

Harbor

MLflow

Trivy

OpenCost

Kubecost

Job description

EY is seeking an AI Systems Engineer to own delivery, model serving, routing, and observability for our AI-native platform. You’ll work across cloud, on‑prem, edge, and air‑gapped environments with a focus on cost, governance, and telemetry.

The role blends DevOps, MLOps, FinOps, and observability, requiring 8+ years in related roles and hands‑on leadership of AI infrastructure at production scale.