Yi Xie
Machine Learning Engineer at TikTok
Bellevue, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolYi Xie is a machine learning engineer with a PhD in computational chemistry and nine years of experience applying advanced math and software engineering to scientific problems. Trained at Georgia Tech and Tsinghua, Yi derived and implemented quantum chemistry algorithms in C++ and Python, scaling SAPT(DFT) methods from small dimers to systems of 100+ atoms by designing out-of-core tensor contraction and block disk I/O strategies. Now at TikTok, Yi brings that numerical rigor to ML engineering, combining deep linear algebra expertise with production coding under Linux/UNIX. Contributions to open-source data tooling include backend pagination and email-cleaning enhancements for the popular dataprep library, reflecting a practical focus on data retrieval and processing. Colleagues value Yi for translating mathematically complex methods into efficient, maintainable code and for solving memory- and I/O-bound challenges that are easy to overlook.
9 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Chemical Physics, 4.0/4.0, Doctor of Philosophy - PhD, Chemical Physics, 4.0/4.0 at Georgia Institute of TechnologyBachelor of Science - BS, Chemistry, 87/100, Bachelor of Science - BS, Chemistry, 87/100 at Tsinghua University
Japanese, English, Chinese
Github Skills (9)
data-preprocessing10
pandas10
dataprep10
data-cleaning10
python10
apidoc9
api9
data-science8
exploratory-data-analysis8
Programming languages (4)
Github contributions (5)
sfu-db/dataprep
Mar 2020 - Apr 2021
Open-source low code data preparation library in python. Collect, clean and visualization your data in python with a few lines of code.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:31 reviews, 28 commits, 31 PRs in 1 year 1 month
Contributions summary:Yi primarily contributed to the data preparation library's back-end functionality by implementing pagination features within the data connector module. They fixed related issues and refined the configuration for pagination on the `ImplicitTable` class. Furthermore, the user added the capability to clean email addresses in `clean_email()` function, enhancing data processing capabilities. These modifications suggest a focus on data retrieval and processing logic.
pythondatadataprepcleaningdatacleaning
xy1994/chatting_room_test
Oct 2017 - Oct 2017
Contributions:14 commits, 12 pushes, 1 branch in 13 days
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.