Senior AI Systems Engineer: DevOps & Observability

Ernst & Young Oman; Grandview Heights (OH); On-site; USD 107,000 - 177,000; Full time

Job summary

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability for its AI-native platform. You’ll operate across cloud, on-prem, edge, and air-gapped environments, shaping how AI services are deployed and governed.

This role intersects DevOps, MLOps, FinOps, and observability, requiring strong pipeline, GPU inference, and cost-visibility skills to ensure repeatable, compliant AI workloads at scale.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with ownership of AI or high-throughput services.
• Hands-on DevOps experience with CI/CD/CV pipelines and GitOps tooling for automated delivery.
• Expertise operating AI/model-serving frameworks on GPU infrastructure.
• Strong observability stack knowledge and OpenTelemetry usage.
• Experience with cost attribution and quota/rate-limits in multi-tenant settings.
• Familiarity with model registries, registry tooling, and governance.

Responsibilities

• Supports DevOps and delivery for AI workloads: CI/CD/CV pipelines, automated build, test, release, and rollback.
• Own governance and discovery for AI assets and model metadata.
• Own resource and cost management to keep AI execution bounded.
• Own the full observability stack: metrics, logs, traces, dashboards.
• Automate GitOps-based delivery with policy gates and automatic rollbacks.
• Ensure end-to-end toll gates align with tenancy and telemetry signals.

Skills

DevOps

MLOps

Observability

GPU inference

OpenTelemetry

Cost / FinOps

Education

Bachelor's/Master's in CS

Tools

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

OpenTelemetry

Job description

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability for its AI-native platform. You’ll operate across cloud, on-prem, edge, and air-gapped environments, shaping how AI services are deployed and governed.

This role intersects DevOps, MLOps, FinOps, and observability, requiring strong pipeline, GPU inference, and cost-visibility skills to ensure repeatable, compliant AI workloads at scale.