Remote AI Systems Engineer - DevOps, Observability

EY; Philadelphia (Philadelphia County); On-site; USD 107,000 - 177,000; Full time

Benefits offered by this job

Hybrid/Remote work

Competitive compensation

Total Rewards

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. You’ll work across cloud, on‑prem, edge, and air‑gapped environments, building automated pipelines and cost-aware governance to ship AI workloads safely and efficiently.

You’ll partner with senior engineers to test and develop capabilities, delivering repeatable, auditable AI workloads with strong emphasis on cost visibility and regulatory compliance.

Qualifications

• 8+ years in DevOps, MLOps, platform, or observability with hands-on ownership of AI workloads.
• CI/CD/CV pipelines and GitOps tooling (ArgoCD, Helm, GitHub Actions/GitLab CI) for automated build, test, release, and rollback.
• Hands-on expertise operating inference/model-serving frameworks (Ray Serve, vLLM, Triton, or NIM) on GPU infrastructure.
• Observability stacks (Prometheus, Grafana, Loki, Tempo/Jaeger) and OpenTelemetry.
• API gateways and request routing (Envoy or equivalent), including streaming responses.
• Cost management / FinOps tooling (OpenCost, Kubecost, or equivalent) and quota/rate-limit enforcement.
• Familiarity with model/artifact registries and supply-chain scanning (Harbor, MLflow, Trivy/SBOM).
• Proven track record operating AI or service infrastructure under compliance, security, or regulatory constraints.
• Define clean ownership boundaries and consumption contracts with platform, trust, and data teams.

Responsibilities

• Support DevOps and delivery for AI workloads; build/operate CI/CD/CV pipelines for AI services, with automated build, test, verification, release, and rollback.
• Own governance and discovery for AI assets, including service catalog/registry, MLflow, Harbor, Trivy, and lineage contracts.
• Own resource and cost management, including quotas and rate limits, cost attribution and utilization to keep AI execution bounded.
• Own the full observability stack: metrics, logs, traces, dashboards, and evaluation tooling like LangSmith/Langfuse.
• Own the OpenTelemetry collection layer, including multi-tenant receiver, exporters, queues, and GPU telemetry.
• Automate GitOps-based delivery and continuous verification with policy gates by default.
• Close the loop between delivery and observability to drive deployment decisions and automated rollbacks.
• Ensure cost and telemetry are per-tenant and attributable end-to-end, tying FinOps to workloads.

Skills

DevOps

MLOps

Observability

FinOps

Compliance

Communication

Education

Bachelor’s or Master’s in CS/related field

Tools

Ray Serve

vLLM

Triton

NIM

Envoy

ArgoCD

Helm

GitHub Actions

GitLab CI

OpenCost

Kubecost

Harbor

MLflow

Trivy

Prometheus

Grafana

Loki

Tempo

Jaeger

LangSmith

Langfuse

DCGM

Job description

EY is seeking an AI Systems Engineer to own delivery, model-serving, routing, and observability for EY’s AI-native platform. You’ll work across cloud, on‑prem, edge, and air‑gapped environments, building automated pipelines and cost-aware governance to ship AI workloads safely and efficiently.

You’ll partner with senior engineers to test and develop capabilities, delivering repeatable, auditable AI workloads with strong emphasis on cost visibility and regulatory compliance.