Senior AI Platform Engineer - Delivery & Observability

EY; Seattle (WA); Remote; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid/Remote work flexibility

Medical and dental coverage

Pension and 401(k)

Job summary

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across cloud, on-prem, edge, and air-gapped environments. You’ll shape how AI services are built, deployed, governed, and observed for repeatable, economical AI workloads.

You’ll drive DevOps, MLOps, and FinOps with pipelines, registries, and OpenTelemetry, partnering with senior engineers to implement secure, observable AI workloads at scale.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on AI/high-throughput ownership.
• Hands-on DevOps experience with CI/CD/CV pipelines and GitOps tooling for automated build, test, release, and rollback.
• In-depth operating inference/model-serving frameworks (Ray Serve, vLLM, Triton, NIM) on GPU infra.
• Strong observability: metrics, logs, traces; OpenTelemetry expertise.
• Experience with API gateways and request routing (Envoy or equivalent).
• Cost management tooling experience (OpenCost, Kubecost) and quota/rate-limit enforcement.
• Familiarity with model/artifact registries (Harbor, MLflow) and SBOM scanning (Trivy).
• Proven track record delivering AI/service infrastructure under compliance constraints.
• Ability to define clear ownership and consumption contracts with platform/trust/data teams.

Responsibilities

• Supports DevOps and delivery for AI workloads by building and operating CI/CD/CV pipelines for AI services and runtime components.
• Own governance and discovery for AI assets and registries (Harbor, MLflow, OpenLineage).
• Own resource and cost management, including quotas, attribution, and utilization.
• Own the full observability stack: metrics, logs, traces, dashboards, and debugging tools.
• Own the OpenTelemetry collection layer for multi-tenant signals and GPU telemetry.
• Automate GitOps-based delivery and verification with policy gates.
• Close the loop between delivery and observability to guide deployment decisions and rollouts.
• Ensure identity-stamped cost and telemetry per tenant for FinOps alignment.

Skills

DevOps

MLOps

Observability

Cost optimization

OpenTelemetry

Governance

Education

Bachelor’s or Master’s in CS or related field

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Jaeger

OpenCost

Kubecost

MLflow

Trivy

Job description

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across cloud, on-prem, edge, and air-gapped environments. You’ll shape how AI services are built, deployed, governed, and observed for repeatable, economical AI workloads.

You’ll drive DevOps, MLOps, and FinOps with pipelines, registries, and OpenTelemetry, partnering with senior engineers to implement secure, observable AI workloads at scale.