AI Platform DevOps Engineer: Delivery & Observability

EY; Wichita (KS); Hybrid; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid work model

Competitive compensation and benefits

Generous paid time off

Job summary

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability across cloud, on‑prem, edge, and air‑gapped environments. You’ll shape the runtime and governance of AI workloads, partnering with senior engineers to test and deploy capabilities.

The role spans DevOps, MLOps, FinOps, and observability, requiring strong pipeline design, GPU inference mastery, and multi‑tenant cost controls. EY offers hybrid work and broad, global opportunities.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with production ownership of AI or high-throughput services.
• Hands-on DevOps experience including CI/CD/CV pipelines and GitOps tooling (ArgoCD, Helm, GitHub Actions/GitLab CI).
• Hands-on expertise operating inference/model-serving frameworks (Ray Serve, vLLM, Triton, or NIM) on GPU infrastructure.
• Strong observability stacks (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.
• Experience with API gateways and request routing (Envoy).
• Experience with cost management / FinOps tooling (OpenCost, Kubecost).
• Familiarity with model/artifact registries and supply-chain scanning (Harbor, MLflow, Trivy).
• Proven track record operating AI or service infrastructure under compliance and security constraints.

Responsibilities

• Supports DevOps and delivery for AI workloads: CI/CD/CV pipelines, automated release and rollback to all environments.
• Own governance and discovery for AI assets including registries, metadata, and license management.
• Own resource and cost management, including quotas, rate limits, and cost attribution per tenant.
• Own the full observability stack: metrics, logs, traces, dashboards, and AI debugging tools.
• Own OpenTelemetry collection layer for multi-tenant telemetry and GPU telemetry (DCGM).
• Automate GitOps-based delivery and continuous verification with policy gates.
• Close the loop between delivery and observability to drive deployment decisions and automated rollbacks.
• Ensure per-tenant identity stamping for FinOps and observability tied to workloads.

Skills

CI/CD pipelines

GitOps

ArgoCD

Helm

GitHub Actions

GitLab CI

Observability

Prometheus

Grafana

Loki

Tempo

Jaeger

OpenTelemetry

Ray Serve

vLLM

Triton

NIM

GPU Inference

FinOps

OpenCost

Kubecost

Harbor

MLflow

Trivy

OpenLineage

Envoy

Education

Bachelor’s or Master’s in CS

Tools

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Job description

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability across cloud, on‑prem, edge, and air‑gapped environments. You’ll shape the runtime and governance of AI workloads, partnering with senior engineers to test and deploy capabilities.

The role spans DevOps, MLOps, FinOps, and observability, requiring strong pipeline design, GPU inference mastery, and multi‑tenant cost controls. EY offers hybrid work and broad, global opportunities.