AI Systems Engineer - DevOps, Delivery & Observability

EY; Kansas City (MO); On-site; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid work model

Medical and dental coverage

401(k) and pension

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, building automated pipelines and secure model execution, with strong focus on cost attribution and telemetry.

You will collaborate with senior engineers to test and develop capabilities, operate high-performance inference, and drive governance and discovery of AI assets in a regulated context.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability engineering with hands-on ownership of AI or high-throughput services.
• Hands-on DevOps experience: CI/CD/CV pipelines and GitOps tooling for automated build, test, release, rollback.
• Hands-on inference/model-serving experience (Ray Serve, vLLM, Triton, NIM) on GPU infra.
• Observability stacks (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.
• Experience with API gateways and request routing (Envoy), incl. streaming responses.
• Experience with cost management / FinOps tooling (OpenCost, Kubecost) and quota/rate-limit enforcement.
• Familiarity with model/artifact registries and supply-chain scanning (Harbor, MLflow, Trivy/SBOM).
• Proven track record in regulated delivery environments.
• Ability to define clean ownership boundaries and consumption contracts with platform/trust/data teams.

Responsibilities

• Supports DevOps and delivery for AI workloads: build and operate CI/CD/CV pipelines that ship AI services and runtime components.
• Own governance and discovery for AI assets and registries, MLflow metadata, registries, and license management.
• Own resource and cost management with quotas and rate limits for tenant-based AI execution.
• Own the full observability stack: metrics, logs, traces, dashboards, and AI debugging tools.
• Own OpenTelemetry collection layer, including multi-tenant receivers and Kafka sinks.
• Automate GitOps-based delivery and verification with policy gates in pipelines.
• Close the loop between delivery and observability to inform deployment decisions and automated rollbacks.
• Ensure cost/telemetry are per-tenant and tied to workloads for FinOps alignment.

Skills

DevOps expertise

MLOps

Observability engineering

Cost optimization

Platform governance

Cross-functional communication

Education

Bachelor’s degree in Computer Science or related

Master’s degree in a related field

Tools

ArgoCD

Helm

GitHub Actions

GitLab CI

Prometheus

Grafana

Loki

Tempo

Jaeger

OpenTelemetry

Harbor

MLflow

Trivy

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, building automated pipelines and secure model execution, with strong focus on cost attribution and telemetry.

You will collaborate with senior engineers to test and develop capabilities, operate high-performance inference, and drive governance and discovery of AI assets in a regulated context.