Contribute to the development of open-source inference frameworks such as SGLang and vLLM, including feature and operator development, performance optimization, and model support in collaboration with the community
Develop and optimize KV cache offloading frameworks for LLM workloads, supporting multi-level cache offloading and reuse across CPU, SSD, and remote storage to improve inference efficiency
Drive R&D on compute performance in distributed training, and explore methods and technologies for performance optimization
Study computational challenges in machine learning systems, identify common needs and bottlenecks, and build example code, acceleration libraries, or frameworks accordingly

Over 3 years working experience in the technology industry
Master’s degree or above in computer science, mathematics, electrical engineering, automation, or related fields.
Strong interest in accelerated computing, parallel computing, and heterogeneous computing
Solid programming skills, good understanding of data structures and computer systems fundamentals
Strong learning agility, adaptability, and the ability to analyze, define, and independently explore technical problems
Familiarity with heterogeneous computing, distributed training, parallel computing, or other high-performance computing areas is a plus
Experience in performance analysis, modeling, or optimization and contributions to open-source frameworks are preferred
Strong ability to define new problems and explore solutions, candidates with independent PhD-level research experience are preferred.
Proficiency with AI coding tools.

Senior Deep Learning Solution Architect

Key skills