Sanxing Chen
Durham, North Carolina, United States
Summary
🤩
Rockstar🎓
Top SchoolSanxing Chen is a PhD candidate in Computer Science at Duke University with a decade of hands-on experience in NLP, language grounding, and relational learning, blending academic research with production-focused engineering. He has interned and worked across Microsoft Research, Microsoft Bing Ads, and Google DeepMind, contributing to LLM agents and exploration research as well as applied recognition systems like microsoft/Recognizers-Text (adding time-unit and phone recognition features). A full-stack contributor, he’s implemented content-export features and admin tooling for the Firekylin blogging platform, showing comfort across backend, frontend, and deployment. Based in Durham, NC, he teaches neuro-symbolic ML and NLP courses, signaling both deep technical expertise and a talent for translating research into curriculum. An NLPer at heart, Sanxing combines research curiosity with pragmatic engineering—often surfacing subtle language issues such as Chinese negative-number handling in production code.
10 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Duke UniversityMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Virginia
Github Skills (20)
javascript10
entity-extraction10
python10
regular-expression10
nodejs10
nlp10
text-parsing10
react10
markdown9
markdown-it9
js9
wordpress8
hexo8
api-design7
webpack7
Programming languages (11)
Github contributions (5)
microsoft/Recognizers-Text
Feb 2018 - Jul 2019
Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV). Packages available at: https://www.nuget.org/profiles/Recognizers.Text, https://www.npmjs.com/~recognizers.text
Role in this project:
Back-end Developer
Back-end DeveloperContributions:134 commits, 139 PRs, 9 pushes in 1 year 5 months
Contributions summary:Sanxing's contributions focus on enhancing the capabilities of the `microsoft/recognizers-text` repository, as evidenced by their work on the `recognizers-text` project, which is for recognizing and resolving text-based entities. They implemented features supporting time units in English with a focus on time-period modifications, and adding phone number recognition capabilities. The user also fixed a Chinese negative number issue.
kebab-casepythoncorpus-linguisticsprefixmicrosoft
firekylin/firekylin
Jun 2017 - Sep 2017
A Simple & Fast Node.js Blogging Platform Base On ThinkJS3 & React & ES2015+
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:7 commits, 7 PRs, 6 comments in 2 months
Contributions summary:Sanxing primarily contributed to the development of the Firekylin blogging platform. They implemented features for exporting content, including Markdown, WordPress WXR, and Hexo/Jekyll formats, and modified the admin interface. This involved backend changes in the `src/admin/controller/api/file.js` and frontend modifications using React components. Additionally, the user made minor CSS adjustments and fixed a MathJax-related regex error.
reactthinkjs3thinkjsnode-jsjavascript
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.