Senior AI Systems Engineer: DevOps, Observability & AI Workloads

EY; Hoboken (NJ); Hybrid; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid work model

Medical and dental coverage

Pension and 401(k)

Job summary

EY is looking for an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY’s AI-native platform. You’ll work across GPU inference, model governance, and multi-environment runtimes, combining DevOps, MLOps, FinOps, and observability.

The role demands strong automation and policy-driven releases in a hybrid, US-wide setting. You’ll own the CI/CD/ CV pipelines, governance for AI assets, cost attribution, telemetry, and multi-tenant OpenTelemetry, ensuring safe,

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on ownership.
• Hands-on CI/CD/CV pipelines and GitOps tooling for automated build, test, release, rollback.
• Hands-on expertise operating inference/model-serving frameworks on GPU infrastructure.
• Strong observability stacks and OpenTelemetry experience.
• Experience with API gateways and request routing, including streaming responses.
• Cost management/FinOps tooling and quota/rate-limit enforcement.
• Familiarity with model/artifact registries and supply-chain scanning.
• Proven track record delivering AI/service infrastructure under compliance and regulation.

Responsibilities

• Supports DevOps and delivery for AI workloads: CI/CD/CV pipelines, automated build/test/release/rollback.
• Own governance and discovery for AI assets and registries (Harbor, MLflow, Trivy, OpenLineage).
• Own resource and cost management with quotas and attribution to tenants and engagements.
• Own full observability stack: Prometheus, Grafana, Loki, Tempo/Jaeger, OpenTelemetry.
• Own OpenTelemetry collection layer and multi-tenant signal routing.
• Automate GitOps-based delivery with quality, integrity, and cost gates in pipelines.
• Link delivery and observability to drive deployment decisions and automated rollback.
• Ensure cost and telemetry are per-tenant and attributable to workloads.

Skills

CI/CD pipelines

OpenTelemetry

Observability

FinOps mindset

AI/workloads governance

Ownership boundaries

Education

Bachelor’s or Master’s degree in Computer Science

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Ray Serve

vLLM

Triton

NIM

MLflow

Harbor

Trivy

OpenLineage

Job description

EY is looking for an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY’s AI-native platform. You’ll work across GPU inference, model governance, and multi-environment runtimes, combining DevOps, MLOps, FinOps, and observability.

The role demands strong automation and policy-driven releases in a hybrid, US-wide setting. You’ll own the CI/CD/ CV pipelines, governance for AI assets, cost attribution, telemetry, and multi-tenant OpenTelemetry, ensuring safe,