Senior AI Systems Engineer: DevOps & Observability

EY; San Francisco (CA); Hybrid; USD 107,000 - 177,000; Full time

Benefits offered by this job

Total Rewards

Hybrid work model

Paid time off

Job summary

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability for its AI-native platform. You will oversee CI/CD pipelines, governance of AI assets, cost attribution, and a comprehensive observability stack across cloud and on‑prem environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring GPU inference expertise and strong collaboration with engineers, architects, and leadership.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering.
• Hands-on CI/CD/CV pipelines and GitOps tooling (ArgoCD, Helm, GitHub Actions).
• Hands-on expertise operating inference/model-serving frameworks on GPUs.
• Strong observability with Prometheus, Grafana, Loki, Tempo/Jaeger.
• Experience with model registries and supply-chain scanning.

Responsibilities

• Build and operate CI/CD/CV pipelines for AI services and runtime components.
• Own governance for AI assets and registries.
• Manage cost attribution and per-tenant quotas.
• Oversee full observability stack with metrics, logs, traces, dashboards.
• Automate GitOps-based delivery with policy gates.

Skills

DevOps

MLOps

Observability

GPU Inference

OpenTelemetry

Cost mgmt

Model governance

CI/CD pipelines

GitOps

APIs

Education

Bachelor's degree in Computer Science or related field

Tools

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Tempo

Jaeger

LangSmith

Langfuse

Harbor

MLflow

Trivy

OpenLineage

Kubecost

OpenCost

Job description

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability for its AI-native platform. You will oversee CI/CD pipelines, governance of AI assets, cost attribution, and a comprehensive observability stack across cloud and on‑prem environments.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring GPU inference expertise and strong collaboration with engineers, architects, and leadership.