Staff Engineer — AI & HPC Compute Infra

Atoms; San Francisco (CA); On-site; USD 224,000 - 284,000; Full time

Benefits offered by this job

Medical, Dental, Vision

Equity

401(k)

Sick Time & PTO

Parental Leave

Commuter Benefit

Job summary

Pronto AI is seeking a hands-on Staff Engineer to build and scale HPC and AI compute infrastructure, spanning hardware, software, networking, and data-center systems. You will own deployment from requirements to production readiness and collaborate across infrastructure, AI, and engineering teams.

The role focuses on designing scalable GPU compute, large-scale CPU compute, and exabyte-scale storage, with emphasis on automation, reliability, and end-to-end implementation. In San Francisco HQ.

Qualifications

• Bachelor's degree or equivalent practical experience in a technical field.
• 8+ years of infrastructure engineering or related disciplines.
• Experience designing, deploying and expanding physical compute infrastructure including HPC clusters or data-center environments.

Responsibilities

• Build AI compute infrastructure from the ground up, including GPU servers and data-center deployments.
• Define the foundation to scale to thousands of GPUs and exabyte-scale storage.
• Own compute and hardware architecture evaluation and rack configurations.
• Design high-performance networking and storage for compute workloads.
• Collaborate with facilities and procurement to translate requirements into specs.

Skills

GPU/CPU clusters

Linux

Networking

Storage

Scripting

Automation tooling

Python

C++

Education

Bachelor's degree in CS/CE/EE or related field

Tools

Python

Go

Bash

C++

Ansible

NVIDIA Base Command Manager

Job description

Pronto AI is seeking a hands-on Staff Engineer to build and scale HPC and AI compute infrastructure, spanning hardware, software, networking, and data-center systems. You will own deployment from requirements to production readiness and collaborate across infrastructure, AI, and engineering teams.

The role focuses on designing scalable GPU compute, large-scale CPU compute, and exabyte-scale storage, with emphasis on automation, reliability, and end-to-end implementation. In San Francisco HQ.