AI Systems Engineer: DevOps, Observability & FinOps Lead

Ernst & Young Oman; Oklahoma City (OK); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Total Rewards package

Paid time off options

Job summary

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability layer of EY’s AI-native platform. You will design and operate CI/CD pipelines, governance, and cost-aware observability across cloud, on‑prem, edge, and air‑gapped environments.

This role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring hands-on delivery of high‑performance AI workloads with repeatable, auditable processes in a regulated context.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or related field.
• 8+ years in DevOps, MLOps, platform, or observability engineering with production ownership of AI or high‑throughput services.
• Hands‑on DevOps experience including CI/CD/CV pipelines and GitOps tooling (ArgoCD, Helm, GitHub Actions/GitLab CI).
• Hands‑on expertise operating inference/model‑serving frameworks on GPU infrastructure (Ray Serve, Triton, NIM).
• Strong observability skills (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.
• Experience with API gateways and request routing (Envoy).
• Experience with cost management tools (OpenCost, Kubecost) and quota enforcement.
• Familiarity with model/artifact registries and governance tools (Harbor, MLflow, Trivy).
• Proven track record operating AI or service infrastructure under regulatory constraints.
• Ability to define ownership boundaries and consumption contracts with platform, trust, and data teams.

Responsibilities

• Own DevOps and delivery for AI workloads across CI/CD/CV pipelines, including automated build, test, verification, release, and rollback.
• Own governance and discovery for AI assets and registries including model metadata and licenses.
• Own resource and cost management with quotas and attribution to tenants/workloads.
• Own the full observability stack: metrics, logs, traces, dashboards, and AI debugging/evaluation tools.
• Own OpenTelemetry collection layer and GPU telemetry for reliable signal routing.
• Automate GitOps-based delivery with policy gates in pipelines.
• Drive deployment decisions with telemetry, evaluation, and cost signals, enabling progressive rollout and automated rollback.
• Ensure per-tenant identity stamping for cost and telemetry alignment.

Skills

DevOps expertise

MLOps experience

Observability

Cost optimization

Strong communicator

Ownership

Education

Bachelor’s or Master’s degree in Computer Science or related field

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Ray Serve

vLLM

Triton

NIM

Envoy

OpenCost

Kubecost

MLflow

Trivy

OpenLineage

Prometheus

Grafana

Loki

Tempo

Jaeger

LangSmith

Langfuse

Job description

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability layer of EY’s AI-native platform. You will design and operate CI/CD pipelines, governance, and cost-aware observability across cloud, on‑prem, edge, and air‑gapped environments.

This role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring hands-on delivery of high‑performance AI workloads with repeatable, auditable processes in a regulated context.