AI Platform Engineer - DevOps, Observability & FinOps

EY; Charleston (WV); Hybrid; 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 EY's AI-native platform. You will work across cloud, on‑prem, edge, and air‑gapped environments, interfacing with DevOps, MLOps, and FinOps teams.

The role emphasizes repeatable, economically bounded AI workloads with strong governance and telemetry. The ideal candidate has 8+ years in DevOps/MLOps, hands-on experience with GPU inference stacks, and expertise in observability and cost visibility.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with production ownership of AI workloads.
• Hands-on DevOps experience including CI/CD 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 and OpenTelemetry.
• Familiarity with model/artifact registries and supply-chain scanning.

Responsibilities

• Supports DevOps and delivery for AI workloads: CI/CD/CV pipelines and release processes.
• Own governance and discovery for AI assets and model metadata.
• Own resource and cost management with quotas and cost attribution.
• Own the full observability stack: metrics, logs, traces, dashboards.
• Own the OpenTelemetry collection layer for multi-tenant environments.
• Automate GitOps-based delivery and verification with policy gates.
• Ensure telemetry and cost signals drive deployment decisions and rollbacks.
• Maintain tenant-scoped cost attribution and SLA visibility.

Skills

DevOps

MLOps

Observability

Model serving

OpenTelemetry

Prometheus

Grafana

Loki

Ray Serve

vLLM

Education

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

Tools

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Tempo

Jaeger

MLflow

OpenTelemetry

Envoy

Harbor

Kubecost

Job description

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY's AI-native platform. You will work across cloud, on‑prem, edge, and air‑gapped environments, interfacing with DevOps, MLOps, and FinOps teams.

The role emphasizes repeatable, economically bounded AI workloads with strong governance and telemetry. The ideal candidate has 8+ years in DevOps/MLOps, hands-on experience with GPU inference stacks, and expertise in observability and cost visibility.