AI Infrastructure Engineer - GPU/Data Center
About this role
Employer-provided description, formatted for easier reading.
AI Infrastructure Engineer in GPU/Data Center
Livermore, CA | Hybrid (Regular Onsite)
Full-Time 4–7 Years of Experience
Only Independent Visa Holders
Strong preference for candidates with hands-on experience deploying or supporting GPU clusters in a data center environment.
We are hiring an experienced
AI Infrastructure Engineer
with strong
hands-on data center experience
to support the deployment, operation, troubleshooting, and maintenance of high-performance GPU infrastructure supporting modern AI workloads.
This is a
hands-on infrastructure role
. Candidates should have practical experience working with
physical servers, GPU systems, Linux, high-speed networking, and data center deployments
— not just cloud or software-based infrastructure.
KEY SKILLS & EXPERINCE:
- Strong Linux Administration – RHEL, Rocky Linux, Ubuntu
- Hands-on experience with
GPU infrastructure
– NVIDIA H100/H200/B200 or AMD Instinct
- Experience with
InfiniBand, RoCEv2, RDMA
, and high-speed networking
- Hands-on server hardware troubleshooting
- Experience with
BMC, IPMI, and Redfish
- Bare-metal provisioning, PXE, and deployment automation
- Python and/or Bash scripting
- Infrastructure automation and configuration
- Data center deployment experience
, including rack installation, cabling, hardware setup, and commissioning
- Tier 2/Tier 3 troubleshooting and root-cause analysis
- Experience supporting production infrastructure in a data center environment
Roles and Responsibilites:
- Deploy and maintain high-performance GPU clusters
- Troubleshoot GPU, Linux, server hardware, and networking issues
- Support physical data center infrastructure and production operations
- Perform hardware installation, configuration, commissioning, and troubleshooting
- Work with high-speed networking technologies including InfiniBand/RDMA/RoCE
- Develop and improve infrastructure automation
- Monitor infrastructure health, reliability, and performance
- Participate in root-cause analysis and resolution of complex infrastructure issues
Preferred Candidates
The ideal candidate is someone who has
actually worked hands-on in a data center environment
and is comfortable working with physical servers, GPU infrastructure, Linux systems, networking, and hardware troubleshooting.