AI Platform Engineer — DevOps, Observability & FinOps

Ernst & Young Oman; Rogers (AR); Hybrid; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid work model

Medical and dental coverage

Pension and 401(k) plans

Job summary

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across EY’s AI-native platform. The role spans CI/CD, governance, cost visibility, and end-to-end observability in cloud/on-prem/edge environments.

The ideal candidate has 8+ years in DevOps/MLOps with hands-on experience in GPU-based inference and OpenTelemetry, operating across hybrid environments.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on ownership of AI or high-throughput services.
• Strong hands-on DevOps experience with CI/CD/CV pipelines and GitOps tooling for automated build, test, release, and rollback.
• Hands-on expertise operating inference/model-serving frameworks on GPU infrastructure.
• Strong experience with observability stacks (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.

Responsibilities

• Supports DevOps and delivery for AI workloads: build and operate CI/CD/CV pipelines and rollbacks.
• Own governance and discovery for AI assets and registries (Harbor, MLflow, Trivy, OpenLineage).
• Own resource and cost management, including quotas and attribution to tenants.
• Own the full observability stack: metrics, logs, traces, dashboards, and LangSmith/Langfuse for evaluation.
• Own OpenTelemetry collection layer and multi-tenant routing for AI signals.
• Automate GitOps-based delivery with policy gates in pipelines.

Skills

DevOps

MLOps

Observability

FinOps

Governance

Education

Bachelors or Masters in CS/related

Tools

Harbor

MLflow

Trivy

Prometheus

Grafana

Job description

EY seeks an AI Systems Engineer to own delivery, model-serving, routing, and observability across EY’s AI-native platform. The role spans CI/CD, governance, cost visibility, and end-to-end observability in cloud/on-prem/edge environments.

The ideal candidate has 8+ years in DevOps/MLOps with hands-on experience in GPU-based inference and OpenTelemetry, operating across hybrid environments.