Wenhan Xiong is a Member of Technical Staff with a decade of experience building and scaling large language models, currently focused on pretraining Grok-{next} at xAI. Previously an AI Research Scientist on Meta’s Llama team, he led long-context pretraining and code fine-tuning efforts that shipped across Meta products and contributed to Llama 2 Long and CodeLlama. An early developer of the xformers library — now a key open-source component for Llama models — he also has a research track record in long-context modeling, multi-hop dense retrieval, and RAG. Trained as an electrical engineer in China and a Ph.D. student in computer science at UC Santa Barbara, Wenhan blends deep research insight with hands-on production engineering at scale. Notably, his work helped operationalize long-context LLMs across consumer surfaces like Messenger and Instagram, bridging cutting-edge research with real-world deployment.
10 years of coding experience
3 years of employment as a software developer
Bachelor's degree Electrical Engineering, Bachelor's degree Electrical Engineering at University of Science and Technology of China
Ph.D. Student Computer Science, Ph.D. Student Computer Science at UC Santa Barbara
Contributions:48 commits, 5 pushes, 1 comment in 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.