Senior AI Platform Infrastructure Engineer

EY; Miami (FL); On-site; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Competitive compensation

Job summary

EY seeks an AI Systems Engineer to design and operate the foundational platform powering EY’s AI-native environment. You’ll manage Kubernetes, bare-metal/GPU infrastructure, and cloud-on-prem deployments across cloud, edge, and air-gapped targets.

Lead the substrate with reliability, portability, and security in regulated contexts, coordinating with security, architecture, and delivery teams. EY offers hybrid work and comprehensive rewards.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or related technical field.
• 8+ years building or operating enterprise infrastructure and large-scale Kubernetes environments.
• Hands-on with Kubernetes distributions (RKE2, EKS/AKS/GKE, K3s) and full cluster lifecycle management.
• Deep experience with bare-metal, cloud, hybrid, on-prem, and air-gapped deployment models.
• Strong grounding in cluster networking (Cilium/CNI), storage, and multi-tenancy isolation.
• Experience with GPU infrastructure and scheduling (NVAIE/DCGM).
• Experience with infrastructure-as-code and GitOps tooling (Terraform/OpenTofu, Helm, ArgoCD, Crossplane).
• Proven track record operating production infrastructure under compliance or regulatory constraints.

Responsibilities

• Own the cluster & cloud-native platform: compute, Kubernetes, scheduling, multi-tenancy.
• Own the infrastructure foundation: Ubuntu/OS, bare-metal, DPU architecture, and NVAIE.
• Stand up EY Agentic AI environments across cloud, on-prem, edge, and air-gapped modes.
• Deliver foundational platform capabilities to support downstream runtime and services.
• Own cluster lifecycle, autoscaling, GPU pooling, and isolation boundaries.
• Secure execution and inference with Ray Serve, vLLM, Triton, and NVIDIA tools; sandboxed execution.
• Oversee cognitive routing: Envoy AI Gateway, semantic routing, model selection, streaming results.
• Collaborate with DevOps on CI/CD, GitOps to keep environments reproducible and drift-free.
• Ensure modular substrate with swappable components to minimize vendor lock-in.

Skills

Kubernetes at scale

Bare-metal & GPU

Multi-tenancy at scale

Infrastructure as code

Security & compliance

Reliability engineering

Effective communication

Education

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

Tools

RKE2

EKS/AKS/GKE

K3s

Terraform/OpenTofu

Helm

ArgoCD

Crossplane

Velero

Job description

EY seeks an AI Systems Engineer to design and operate the foundational platform powering EY’s AI-native environment. You’ll manage Kubernetes, bare-metal/GPU infrastructure, and cloud-on-prem deployments across cloud, edge, and air-gapped targets.

Lead the substrate with reliability, portability, and security in regulated contexts, coordinating with security, architecture, and delivery teams. EY offers hybrid work and comprehensive rewards.