英伟达Senior Solutions Architect - KV Cache and AI Storage
社招全职地点:北京状态:招聘
工作描述
任职要求 • Bachelor's degree or higher in Computer Science or a related field with strong systems or storage background. • 5+ years of relevant experience, including 2+ years passionate about KV stores/caches or storage backends. • Hands‑on experience with distributed storage, caching, or large‑scale backend systems. • Solid understanding of Transformer / LLM inference and KV cache concepts, plus experience with at least one LLM serving stack (for example vLLM, TensorRT‑LLM or SGLang). • Strong knowledge of NVMe SSDs, KV SSDs, and modern storage servers, including controller/firmware behavior and I/O characteristics. • Practical experience with tiered memory and KV cache optimizations such as offloading (HBM → DRAM → NVMe), eviction/selection strategies, compression/quantization, or attention‑level optimizations. • Familiarity with at least one large…
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
Transformer+
https://huggingface.co/learn/llm-course/en/chapter1/4
Breaking down how Large Language Models work, visualizing how data flows through.
https://poloclub.github.io/transformer-explainer/
An interactive visualization tool showing you how transformer models work in large language models (LLM) like GPT.
https://www.youtube.com/watch?v=wjZofJX0v4M
Breaking down how Large Language Models work, visualizing how data flows through.
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
缓存+
https://hackernoon.com/the-system-design-cheat-sheet-cache
The cache is a layer that stores a subset of data, typically the most frequently accessed or essential information, in a location quicker to access than its primary storage location.
https://www.youtube.com/watch?v=bP4BeUjNkXc
Caching strategies, Distributed Caching, Eviction Policies, Write-Through Cache and Least Recently Used (LRU) cache are all important terms when it comes to designing an efficient system with a caching layer.
https://www.youtube.com/watch?v=dGAgxozNWFE
vLLM+
https://www.newline.co/@zaoyang/ultimate-guide-to-vllm--aad8b65d
vLLM is a framework designed to make large language models faster, more efficient, and better suited for production environments.
https://www.youtube.com/watch?v=Ju2FrqIrdx0
vLLM is a cutting-edge serving engine designed for large language models (LLMs), offering unparalleled performance and efficiency for AI-driven applications.
TensorRT+
https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/quick-start-guide.html
This TensorRT Quick Start Guide is a starting point for developers who want to try out the TensorRT SDK; specifically, it demonstrates how to quickly construct an application to run inference on a TensorRT engine.
还有更多 •••
相关职位
社招
• Bachelor’s/Master’s/PhD degree in Computer Science, Computer Engineering, Electrical Engineering,
更新于 2026-07-01上海
社招
• BS/MS/PhD in Engineering, Mathematics, Physics, or Computer Science, or equivalent experience • 5&
更新于 2026-07-07上海|北京
社招
• BS/MS/PhD in Engineering, Mathematics, Physics, or Computer Science, or equivalent experience • 5&
更新于 2026-07-11北京