17 days ago
Shanghai, China or Beijing, ChinaSenior
Responsibilities
- Contribute feature and operator development, model support, and performance optimization to open-source inference frameworks such as SGLang and vLLM.
- Develop and optimize multi-level KV cache offloading and reuse across CPU, SSD, and remote storage for LLM inference through the FlexKV project.
- Conduct R&D on compute performance and optimization methods for distributed training.
- Analyze computational challenges and bottlenecks in machine learning systems and build example code, acceleration libraries, or frameworks.
- Design AI computing platform architectures and help solve customer computational challenges in LLM inference, training acceleration, network communication, and data transfer.
Requirements
- More than 5 years of technology industry experience.
- Master's degree or higher in computer science, mathematics, electrical engineering, automation, or a related field.
- Strong interest in accelerated, parallel, heterogeneous, and high-performance computing.
- Solid programming skills and understanding of data structures and computer systems fundamentals.
- Ability to learn, adapt, analyze, define, and independently explore technical problems.
- Familiarity with distributed training, parallel computing, heterogeneous computing, or related high-performance computing areas is preferred.
- Experience in performance analysis, performance modeling, performance optimization, or open-source framework contributions is preferred.
- Independent PhD-level research experience and proficiency with AI coding tools are preferred.
Benefits
- Competitive salary and a generous benefits package.
Categories
Solutions Engineering
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.