Senior Solutions Architect - Kv Cache And Ai Storage

NVIDIA

Not specified
Llm inference platforms
Kv cache solutions
Nvidia modern networking technologies
NVIDIA is seeking a Senior Solutions Architect specializing in KV cache and AI storage to collaborate with customers in developing cutting-edge LLM inference platforms. The ideal candidate will have a strong systems or storage background and relevant experience in building and optimizing caching solutions

Job Summary

  • Collaborate closely with our largest customers to build next-generation LLM inference platforms powered by NVIDIA GPUs, Dynamo/KVBM, and CMX.
  • Lead technical exploration with customer architects to understand models, frameworks, SLOs, and KV cache usage patterns.
  • With competitive salaries and a generous benefits package, we are widely considered to be one of the world’s most desirable employers!

Matching Summary

Match Score: 85

NVIDIA is seeking a Senior Solutions Architect specializing in KV cache and AI storage to collaborate with customers in developing cutting-edge LLM inference platforms. The ideal candidate will have a strong systems or storage background and relevant experience in building and optimizing caching solutions.

Skills & Requirements

Must-have

  • LLM inference platforms
  • KV cache solutions
  • NVIDIA modern networking technologies
  • Transformer / LLM inference
  • NVMe SSDs, KV SSDs
  • tiered memory optimizations

Nice-to-have

  • large-scale online services
  • custom KV stores/cache layers
  • NVIDIA Triton Inference Server
  • public talks, papers, blogs

Key Requirements

  • Bachelor's degree or higher
  • 5+ years of relevant experience
  • 2+ years passionate about KV stores/caches
  • Hands-on experience with distributed storage
  • Experience with at least one LLM serving stack

Work Rights

Not specified

Tailored Resume

Cover Letter