Senior AI Factory Architect - Multi-GPU Benchmarking

NVIDIA; Santa Clara (CA); On-site; USD 152,000 - 287,500; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Senior Solutions Architect to join the Infrastructure Specialists team. You will support AI factories, run and verify AI/LLM workloads on Linux GPU clusters, and analyze NCCL collectives for performance scaling.

You’ll build observability and automation, troubleshoot challenging benchmarks, and collaborate with cross-functional teams to prepare AI factories for customers, delivering validated hardware and software configurations. Equity and benefits are included.

Qualifications

• Bachelor’s degree or equivalent experience in a related field (CS, Math, Eng, Physics).
• 5+ years of experience managing Linux-based HPC or distributed systems.
• Hands-on experience running AI/ML workloads on multi-GPU/multi-node clusters.
• Familiarity with NCCL and collectives in ML/LLM training.
• Strong scripting in Python and Shell/Bash; good cross-team communication.

Responsibilities

• Set up and verify AI factory environments across multi-GPU Linux clusters.
• Validate NCCL configurations and distributed training frameworks.
• Run AI/LLM benchmarks, orchestrate runs, collect results and analyze.
• Troubleshoot failing or underperforming training jobs and benchmarks.
• Improve observability with metrics, logs, and dashboards for workloads.
• Build automation using Python and Shell for benchmarks and regression checks.
• Analyze NCCL usage and parallelism to improve throughput and scaling.
• Collaborate across hardware, software, networking, and product teams.
• Contribute to internal/customer-facing readiness materials and docs.

Skills

Linux HPC

Distributed systems

AI/ML workloads

NCCL collectives

Python

Shell/Bash

Communication

Education

Bachelor's degree

Tools

NCCL

Job description

NVIDIA is seeking a Senior Solutions Architect to join the Infrastructure Specialists team. You will support AI factories, run and verify AI/LLM workloads on Linux GPU clusters, and analyze NCCL collectives for performance scaling.

You’ll build observability and automation, troubleshoot challenging benchmarks, and collaborate with cross-functional teams to prepare AI factories for customers, delivering validated hardware and software configurations. Equity and benefits are included.