Senior AI Platform Infrastructure Engineer

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

Benefits offered by this job

Hybrid/Remote work options

Total Rewards package

Paid time off

Medical and dental coverage

Job summary

EY is seeking an AI Systems Engineer to build and operate EY’s AI-native platform substrate across cloud, on-prem, edge, and air-gapped targets. You’ll own the Kubernetes stack, cluster fabric, and multi-tenancy, delivering scalable, reliable infrastructure for Agentic AI workloads.

The role requires deep expertise in cloud-native platforms, GPU/ DPU infrastructure, and GitOps, with a focus on portability, security, and regulatory compliance. 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, cloud platforms, or large-scale Kubernetes environments.
• Hands-on expertise with Kubernetes distributions (RKE2, EKS/AKS/GKE, K3s) and full cluster lifecycle management.
• Deep experience with bare-metal, cloud, hybrid, on-prem, and ideally air-gapped deployment models.
• Strong grounding in cluster networking (Cilium/service mesh/CNI), storage, and multi-tenancy isolation.
• Experience with GPU infrastructure and scheduling (NVAIE/DCGM, GPU operators, virtualization/MIG).
• Experience with infrastructure-as-code and GitOps tooling (Terraform/OpenTofu, Helm, ArgoCD, Crossplane).
• Proven track record operating production infrastructure under compliance, security, or regulatory constraints.
• Ability to work effectively with security, architecture, product, and delivery teams.

Responsibilities

• Own the cluster & cloud-native platform: compute, Kubernetes and scheduling, cluster fabric/networking, multi-tenancy, and distributed compute.
• Own the infrastructure foundation: Ubuntu/OS, BMC/bare-metal, DPU architecture, and NVAIE (GPU/Network/DCGM).
• Stand up and manage EY Agentic AI environments across cloud (EKS/AKS/GKE), on-prem AI Factory (RKE2/NVAIE), edge (K3s), and air-gapped deployment modes.
• Deliver foundational platform capabilities such as Infrastructure Management, Kubernetes & Scheduling, and Cluster Fabric Management.
• Own cluster lifecycle, autoscaling, GPU pooling/virtualization, and multi-tenancy boundaries (vCluster/Crossplane/Karpenter).
• Own secure execution and inference: Ray Serve, vLLM/NIM/Triton, and NVIDIA Dynamo, with sandboxed execution (gVisor/Firecracker...).
• Own cognitive and routing: Envoy AI Gateway, semantic routing (vLLM-SR), model/prompt selection, and streaming response handling.
• Collaborate with DevOps Engineers on deployment and delivery of the platform itself: CI/CD/CV (ArgoCD), IaC/GitOps (Helm/OpenTofu).
• Own backup, disaster recovery, and cross-environment replication (Velero, CloudNativePG, Cilium ClusterMesh).
• Ensure the substrate is modular and swappable, minimizing vendor lock-in while preserving stack contract.

Skills

Kubernetes

Cloud-native

Multi-tenancy

Bare-metal

GPU infrastructure

Education

Bachelor’s or Master’s in Computer Science

Tools

RKE2

EKS/AKS/GKE

K3s

Terraform/OpenTofu

Helm

ArgoCD

Crossplane

Velero

Cilium

Job description

EY is seeking an AI Systems Engineer to build and operate EY’s AI-native platform substrate across cloud, on-prem, edge, and air-gapped targets. You’ll own the Kubernetes stack, cluster fabric, and multi-tenancy, delivering scalable, reliable infrastructure for Agentic AI workloads.

The role requires deep expertise in cloud-native platforms, GPU/ DPU infrastructure, and GitOps, with a focus on portability, security, and regulatory compliance. EY offers hybrid work and comprehensive rewards.