Mingyang Wan
SWE at Neeva
College Station, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolMingyang Wan is a software engineer with six years of experience building data-driven systems and machine learning pipelines, currently working at Neeva after an SDE internship at Apple. He holds a Master’s in Industrial Engineering from Texas A&M and has driven measurable impact in industry roles—from saving $30k and streamlining reporting at Bristol-Myers Squibb to optimizing logistics pipelines at JD.com. His technical toolkit spans Python, R, SQL, NLP, TensorFlow/Keras, and AWS, and he contributes to open-source ML tooling such as TODS, where he added ensemble methods to improve time-series outlier detection. Comfortable moving projects from research to production, he blends data science rigor with software engineering practices and a knack for turning complex pipelines into reliable, testable systems. Notably, he has experience developing visualization and BI solutions that boosted operational efficiency by 80%, underscoring his focus on actionable analytics.
6 years of coding experience
3 years of employment as a software developer
Bachelor's degree, Automation Engineer Technology/Technician, Bachelor's degree, Automation Engineer Technology/Technician at Beijing University of Posts and TelecommunicationsMaster of Engineering - MEng, Industrial Engineering, Master of Engineering - MEng, Industrial Engineering at Texas A&M University
Github Skills (9)
machine-learning10
time-series10
ensembles10
anomaly-detection10
python10
scikit-learn9
scikit9
automl8
automated-machine-learning8
Programming languages (2)
Github contributions (5)
datamllab/tods
Sep 2020 - Jan 2021
TODS: An Automated Time-series Outlier Detection System
Role in this project:
ML Engineer
ML EngineerContributions:7 commits, 1 PR, 6 pushes in 3 months
Contributions summary:Mingyang primarily focused on integrating and extending ensemble methods within the time-series outlier detection pipeline. This involved modifying existing code, specifically creating a pipeline, and adding ensemble methods in order to improve the accuracy of the detection algorithms. The user added the Ensemble class and updated the pipeline to use it. This work directly supports the project's goal of automated time-series anomaly detection.
time-series-analysisoutlier-detectionanomaly-detectionmachine-learningoutlier
datamllab/rlcard-tutorial
Jun 2020 - Mar 2022
Contributions:64 commits, 3 pushes in 1 year 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.