AI Systems Engineer - DevOps, Observability & AI Runtime

Ernst & Young Oman; Westlake Village (CA); Hybrid; USD 107,000 - 177,000; Full time

Job summary

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across EY’s hybrid AI platform. You will shape how AI services are built, executed, and governed in cloud, on‑prem, edge, and air‑gapped environments.

This role combines DevOps, MLOps, FinOps, and observability, requiring strong GPU Inference, OpenTelemetry, and cost‑aware delivery. You’ll collaborate with cross‑functional teams to ensure repeatable, compliant workloads.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on ownership of AI or high-throughput services.

Responsibilities

• Supports DevOps and delivery for AI workloads: build and operate CI/CD/CV pipelines for AI services, agents, and runtime components.
• Own governance and discovery for AI assets, including model metadata and registries.
• Own resource and cost management, including quotas and rate limits for AI workloads.
• Own the full observability stack: metrics, logs, traces, dashboards, and SLA/alert notifications.
• Own OpenTelemetry collection layer for reliable signal routing across environments.
• Automate GitOps-based delivery and verification with policy gates.
• Close the loop between delivery and observability using telemetry and cost signals for deployment decisions.
• Ensure cost and telemetry are per-tenant and auditable across workloads.

Skills

DevOps pipelines

AI inference systems

OpenTelemetry

Cost management

Model governance

CI/CD

Registries

Cloud/on-prem

Education

Bachelor’s or Master’s in CS

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

OpenTelemetry

Job description

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across EY’s hybrid AI platform. You will shape how AI services are built, executed, and governed in cloud, on‑prem, edge, and air‑gapped environments.

This role combines DevOps, MLOps, FinOps, and observability, requiring strong GPU Inference, OpenTelemetry, and cost‑aware delivery. You’ll collaborate with cross‑functional teams to ensure repeatable, compliant workloads.