Cluster Architect (Fully Remote)

Andromeda Cluster; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Unlimited PTO

Comprehensive benefits

Job summary

Andromeda invites a senior engineer to own GPU cluster reference designs and translate workloads and site constraints into compute, fabric, storage, and power architectures.

You will help define cross-site reference designs, collaborate with vendors, and contribute to scalable AI infrastructure across platforms.

Qualifications

• Experience delivering 1,000+ GPU clusters with NVIDIA platforms.
• Knowledge of InfiniBand, parallel storage, Slurm/Kubernetes, and facilities.

Responsibilities

• Turn workloads and site constraints into compute, fabric, storage, and power designs.
• Define reference designs across sites, vendors, and platforms.

Skills

GPU clustering

NVIDIA platforms

Tools

InfiniBand

Slurm

Kubernetes

Parallel storage

Job description

• Own standard and custom GPU cluster reference designs.
• Turn workloads and site constraints into compute, fabric, storage, and power designs.

What We're Looking For:

• Experience delivering 1,000+ GPU clusters with NVIDIA platforms.
• Knowledge of InfiniBand, parallel storage, Slurm/Kubernetes, and facilities.

Why You'll Love It Here:

• Define reference designs across sites, vendors, and platforms.
• High-talent-density team with comprehensive benefits and unlimited PTO.

Andromeda is a market and infrastructure platform for buying, selling, and operating compute. It is a high-trust, high-talent-density team shaping the AI infrastructure market with comprehensive benefits and an inclusive culture.