Senior GPU Cloud Infra Engineer: Multi-Tenancy & Orchestration

Hyperbolic; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Hyperbolic is seeking a very senior Infrastructure Engineer to architect and scale our GPU Cloud Marketplace. You will design a multi-tenancy provisioning and virtualization layer that turns diverse GPUs into a programmable pool for thousands of developers.

You’ll work at the cutting edge of cloud infra, building the core orchestration to deliver significant cost savings versus traditional providers while collaborating across hardware vendors and internal teams.

Qualifications

• Experience with bare-metal provisioning and lifecycle management.
• Experience with GPU scheduling and orchestration.
• Strong Terraform or Pulumi skills and CI/CD for infrastructure.
• Experience with AI/ML storage and distributed file systems.
• API design and cloud-init for automated provisioning.
• Knowledge of CUDA and GPU compute optimization.
• Collaborative team player with clear communication.
• Experience integrating with hardware vendors.
• Experience building and scaling cloud infrastructure.

Responsibilities

• Build multi-tenant provisioning and virtualization solutions.
• Develop the core orchestration layer for the GPU cloud.
• Transform raw GPUs into a programmable, scalable pool.
• Collaborate with hardware vendors and engineering teams.
• Drive cost efficiency, targeting savings over traditional clouds.

Skills

Bare-metal provisioning

GPU scheduling

Terraform

CI/CD

Observability

AI/ML storage

API design

CUDA

Vendor collaboration

Distributed systems

Tools

Pulumi

IPMI

Redfish

PXE boot

Ceph

Weka

Job description

Hyperbolic is seeking a very senior Infrastructure Engineer to architect and scale our GPU Cloud Marketplace. You will design a multi-tenancy provisioning and virtualization layer that turns diverse GPUs into a programmable pool for thousands of developers.

You’ll work at the cutting edge of cloud infra, building the core orchestration to deliver significant cost savings versus traditional providers while collaborating across hardware vendors and internal teams.