AI Platform Engineer — DevOps, Observability & FinOps

EY; Houston (TX); Hybrid; USD 107,000 - 177,000; Full time

Benefits offered by this job

Medical and dental coverage

Hybrid work model

Paid time off

Job summary

EY is seeking an AI Systems Engineer to own delivery, model serving, routing, and observability for EY’s AI-native platform across cloud, on‑prem, edge, and air‑gapped environments. You will shape CI/CD/CV pipelines, governance, and telemetry to ensure repeatable, economical AI workloads.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring strong experience with GPUs, model serving, and multi‑environment runtimes.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands‑on production ownership of AI or high‑throughput services.

Responsibilities

• Supports DevOps and delivery for AI workloads: build and operate CI/CD/CV pipelines and automated release for AI services and runtimes.
• Own governance and discovery for AI assets including registries, model metadata, and SBOM scanning.
• Own resource and cost management with quotas, rate limits, and cost attribution.
• Own the full observability stack: metrics, logs, traces, dashboards, and evaluation tooling.
• Own OpenTelemetry collection including multi‑tenant routing and GPU telemetry.
• Automate GitOps delivery with policy gates and automated verification.
• Close the loop between delivery and observability using telemetry and cost signals for rollout decisions.
• Ensure per‑tenant identity stamping for FinOps and observability.

Skills

CI/CD pipelines

GitOps

Observability

OpenTelemetry

Cost governance

GPU inference

Model serving

Registry governance

Cloud & on‑prem

Education

Bachelor's in CS

Master's (benefit)

Tools

Ray Serve

Triton

vLLM

LangSmith

Langfuse

Prometheus

Grafana

Loki

Envoy

Job description

EY is seeking an AI Systems Engineer to own delivery, model serving, routing, and observability for EY’s AI-native platform across cloud, on‑prem, edge, and air‑gapped environments. You will shape CI/CD/CV pipelines, governance, and telemetry to ensure repeatable, economical AI workloads.

The role sits at the intersection of DevOps, MLOps, FinOps, and observability, requiring strong experience with GPUs, model serving, and multi‑environment runtimes.