AI Platform Delivery Engineer & Observability Lead

EY; Irvine (CA); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

401(k) matching

Paid time off options

Job summary

EY in the United States seeks an AI Systems Engineer to own the delivery, model-serving, routing, and observability layer of EY’s AI-native platform. This role covers CI/CD, governance, cost controls, and multi-environment runtime across cloud, on-prem, edge, and air‑gapped environments.

You will operate high‑performance inference, implement automated pipelines, and deliver transparent telemetry in a hybrid, globally connected team. EY offers a hybrid model and broad development opportunities.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or related field.
• 8+ years in DevOps, MLOps, platform, or observability engineering with production ownership.
• Hands-on DevOps experience with CI/CD/CV pipelines and GitOps tooling (ArgoCD, Helm, GitHub Actions, or equivalents).
• Hands-on expertise operating inference/model-serving frameworks (Ray Serve, vLLM, Triton, or NIM) on GPU.
• Strong observability experience (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.
• Experience with API gateways and routing (Envoy) including streaming responses.
• Experience with cost tooling (OpenCost, Kubecost) and quota enforcement.
• Familiarity with model registries and supply-chain scanning (Harbor, MLflow, Trivy).
• Proven track record delivering AI or service infra under compliance and security constraints.
• LLM evaluation and debugging tooling (LangSmith, Langfuse).
• Sandboxed/secure execution (gVisor, Firecracker) for multi-tenant workloads.
• GPU telemetry (DCGM) and GPU utilization optimization.
• OpenLineage governance and AI license management.
• Multi-tenant cost attribution and per-tenant SLA/alerting.
• Exposure to regulated delivery environments (financial services, tax, healthcare, risk).

Responsibilities

• Own DevOps and delivery for AI workloads with CI/CD/CV pipelines and rollout.
• Own governance and discovery for AI assets and registries.
• Own resource and cost management with quotas and attribution.
• Own the full observability stack: metrics, logs, traces, dashboards.
• Own OpenTelemetry collection layer across multi-tenant environments.
• Automate GitOps-based delivery with policy gates in pipelines.
• Close loop between delivery and observability to drive deployment decisions.
• Ensure cost and telemetry are per-tenant and attributable.

Skills

DevOps expertise

MLOps

Observability

FinOps mindset

OpenTelemetry

Governance & registries

Multi-environment

Communication

Education

Bachelor’s or Master’s degree in Computer Science

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Tempo/Jaeger

Envoy

Harbor

MLflow

Trivy

OpenLineage

Kubecost

OpenCost

DCGM

Job description

EY in the United States seeks an AI Systems Engineer to own the delivery, model-serving, routing, and observability layer of EY’s AI-native platform. This role covers CI/CD, governance, cost controls, and multi-environment runtime across cloud, on-prem, edge, and air‑gapped environments.

You will operate high‑performance inference, implement automated pipelines, and deliver transparent telemetry in a hybrid, globally connected team. EY offers a hybrid model and broad development opportunities.