AI Delivery & Observability Architect

EY; Pittsburgh (Allegheny County); On-site; USD 126,000 - 262,000; Full time

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 manage CI/CD pipelines, governance, cost attribution, and comprehensive observability across cloud, on-prem, edge, and air-gapped environments.

Ideal candidates have deep DevOps/MLOps experience with GPU-enabled inference, OpenTelemetry, and multi-tenant cost controls, and can operate in regulated contexts while driving scalable, observable AI workloads.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or related technical field.
• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on ownership of AI or high-throughput services.
• Hands-on DevOps experience including 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 observability experience with Prometheus, Grafana, Loki, Tempo/Jaeger.
• Experience with API gateways and request routing including streaming responses.
• Experience with cost management tools and quota/rate-limit enforcement.
• Familiarity with model/artifact registries and supply-chain scanning.
• Proven track record delivering AI or service infrastructure under compliance and regulatory constraints.

Responsibilities

• Own DevOps and delivery for AI workloads, including CI/CD/CV pipelines and automated release processes.
• Own governance and discovery for AI assets (registries, metadata, licenses).
• Own resource and cost management with per-tenant attribution and quotas.
• Own the full observability stack: metrics, logs, traces, dashboards, and OpenTelemetry.
• Own OpenTelemetry collection and multi-tenant data routing for reliable signal capture.
• Automate GitOps-based delivery with policy gates in pipelines.
• Close the loop between delivery and observability to drive deployment decisions and automated rollbacks.
• Ensure consumption signals are per-tenant and aligned with FinOps and observability goals.

Skills

DevOps

GitOps

OpenTelemetry

Ray Serve

vLLM

Triton

NIM

GPU deployment

Observability

Cost governance

Education

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

Tools

Prometheus

Grafana

Loki

Tempo/Jaeger

Harbor

MLflow

Trivy

Kubecost/OpenCost

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 manage CI/CD pipelines, governance, cost attribution, and comprehensive observability across cloud, on-prem, edge, and air-gapped environments.

Ideal candidates have deep DevOps/MLOps experience with GPU-enabled inference, OpenTelemetry, and multi-tenant cost controls, and can operate in regulated contexts while driving scalable, observable AI workloads.