Wenxuanย Li
Research Intern at Microsoft
Cambridge, England, United Kingdom
Summary
๐คฉ
Rockstar๐
Top SchoolWenxuan Li is a research-focused software engineer with six years of experience building and scaling multi-agent AI systems and LLM infrastructure. Currently a Research Intern at Microsoft and an MPhil candidate in Advanced Computer Science at Cambridge, he has hands-on experience in efficient distributed long-context LLM training and dynamic sparse attention. His internships at KAUST and Alibaba Cloud involved integrating function-calling into agent frameworks and supporting large-scale generative model infrastructure, respectively. An active open-source contributor, he enhanced the prominent CAMEL multi-agent framework by adding multilingual role-playing capabilities that enable diverse language models to collaborate. Wenxuan combines rigorous academic training with practical backend engineering, often bridging LLM research prototypes to deployable agent ecosystems. Heโs particularly skilled at making multi-LLM systems interoperable with external inference servers and real-world tooling.
6 years of coding experience
1 year of employment as a software developer
Bachelor of Science with Honours, Artificial Intelligence and Computer Science, Bachelor of Science with Honours, Artificial Intelligence and Computer Science at The University of EdinburghMaster of Philosophy - MPhil, Advanced Computer Science, Master of Philosophy - MPhil, Advanced Computer Science at University of Cambridge
Github Skills (8)
agent10
large-language-models10
python10
natural-language-processing10
multi-agent9
multiagent-systems9
deep-learning6
deeplearning-ai6
Programming languages (3)
Github contributions (5)
camel-ai/camel
May 2023 - Oct 2023
๐ซ CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Role in this project:
Back-end Developer
Back-end DeveloperContributions:76 reviews, 15 PRs, 84 pushes in 4 months
Contributions summary:Wenxuan contributed to the `camel-ai/camel` repository by implementing multi-lingual role-playing capabilities. The commits involve modifications to the `camel/societies/role_playing.py`, `camel/agents/chat_agent.py`, `camel/agents/task_agent.py` and the addition of a new example `examples/ai_society/role_playing_multi_lingual.py`. These changes included incorporating output language specifications, enabling the agents to function in different languages. The user's work directly enhanced the framework's ability to support diverse language models and tasks.
agentai-societiesartificial-intelligencecommunicative-aicooperative-ai
HalberdOfPineapple/CamDB
Jan 2024 - Jun 2024
Contributions:180 pushes in 4 months
Find and Hire Top DevelopersWeโve 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.