Prime Intellect
Member of Technical Staff - GPU Infrastructure
$300K
San Francisco +3 · Remote · Staff · Full-time · Posted Jul 8, 2026
- Location
- San Francisco
Remote
APAC
United States - Experience
- 3+ years hands-on experience with GPU clusters and HPC environments.
- Visa sponsorship
- Full visa sponsorship and relocation support.
About the job
Design, deploy, optimize, and support GPU clusters for customers running AI training, inference, and HPC workloads.
What you'll do
- Design GPU cluster architectures, capacity plans, and deployment strategies with customers.
- Deploy and tune orchestration, networking, storage, and GPU systems for distributed workloads.
- Resolve customer infrastructure issues, provide on-call support, and create operational documentation.
What they ask for
- 3+ years of hands-on experience with GPU clusters and HPC environments.
- Deep expertise with SLURM and Kubernetes in production GPU settings, plus InfiniBand configuration and troubleshooting.
- Strong understanding of NVIDIA GPU architecture, CUDA, and drivers; experience with Ansible and Terraform.
- Proficiency in Python, Bash, and systems programming; track record of customer-facing technical leadership.
Nice to have
- Experience with 1000+ GPU deployments or NVIDIA DGX, HGX, or SuperPOD certification.
- Experience with distributed training frameworks, AMD MI300 or Intel Gaudi, or open-source HPC/AI infrastructure.
Pay
$150-300k (cash compensation; base salary or total pay not specified)
Tools
SLURM, Kubernetes, InfiniBand, RoCE, NVLink, Lustre, BeeGFS, GPFS
AI focus
Supports infrastructure for LLM training, inference, and HPC workloads, including frontier AI research.
Model-written summary · the original posting is authoritative