AI Systems Engineer: DevOps, Observability & FinOps

EY; Tucson (AZ); Híbrido; USD 107 000 - 177 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Hybrid work model

Total Rewards package

Resumo da oferta

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability across EY’s AI-native platform. You will ship, run, and observe AI workloads from cloud to edge, coordinating with senior engineers to advance capabilities.

This role sits at the intersection of DevOps, MLOps, FinOps, and observability, demanding hands-on automation, secure model execution, and end-to-end governance across environments.

Qualificações

• 8+ years in DevOps, MLOps, platform, or observability with hands-on ownership of AI workloads.
• Hands-on CI/CD/CV pipelines and GitOps tooling for automated build, test, release, rollback.
• Experience with GPU inference and model-serving frameworks on production infra.
• Strong observability experience with Prometheus, Grafana, Loki, Tempo/Jaeger and OpenTelemetry.
• Experience with API gateways and request routing (Envoy) including streaming responses.
• Experience with FinOps tools and cost attribution/enforcement.
• Familiarity with model/artifact registries and supply-chain scanning.
• Proven track record delivering AI/service infrastructure under compliance constraints.
• Ability to define ownership strata and consumption contracts across teams.

Responsabilidades

• Own DevOps and delivery for AI workloads: CI/CD/CV pipelines, automated build, test, release, rollback.
• Manage governance and discovery for AI assets and registries.
• Control resource usage and cost attribution to keep AI execution bounded.
• Own the full observability stack: metrics, logs, traces, dashboards.
• Own OpenTelemetry collection, multi-tenant receivers and GPU telemetry pipelines.
• Automate GitOps-based delivery with quality and cost gates.
• Link delivery and observability to drive deployment decisions and automated rollbacks.
• Ensure identity-stamped cost telemetry and per-tenant accountability.

Conhecimentos

DevOps

Model-serving

Observability

FinOps

Governance

Multi-environment

Communication

Formação académica

Bachelor’s or Master’s in Computer Science

Ferramentas

Ray Serve

vLLM

Triton

NIM

Prometheus

Grafana

Loki

Tempo/Jaeger

OpenTelemetry

Envoy

OpenCost

Kubecost

Harbor

MLflow

Trivy

Descrição da oferta de emprego

EY is seeking an AI Systems Engineer to own the delivery, model-serving, routing, and observability across EY’s AI-native platform. You will ship, run, and observe AI workloads from cloud to edge, coordinating with senior engineers to advance capabilities.

This role sits at the intersection of DevOps, MLOps, FinOps, and observability, demanding hands-on automation, secure model execution, and end-to-end governance across environments.