# Tianpei Xia

> ML Software Engineer, PhD

Location: Mountain View, California, United States
Profile: https://flows.cv/tianpei

I'm currently working as a software engineer at NewsBreak. Before that, I was an NSF-funded Ph.D. researcher in the Department of Computer Science at North Carolina State University under the supervision of Dr. Tim Menzies. My research interests include using data mining and artificial intelligence methods to solve real-world problems in the software engineering field. Such as exploring new techniques in search-based optimization to improve the performance of current SE predicting tasks (like effort estimation, text mining, etc.).

I'm interested in applying state-of-the-art models to solve real-world problems,  productionalize and ship models, and building large-scale software infrastructures.

Skill sets: Python, Java, JavaScript, AWS, Docker, MySQL, NoSQL, Linux, Git, Jenkins, Spark, Grafana, Kafka
ML frameworks: Scikit-learn, Pytorch, Tensorflow/Keras
ML experience: Data analytics, Visualization, Supervised/unsupervised modeling, machine learning model optimization

More details: http://xiatianpei.com/

## Work Experience
### Software Engineer @ NewsBreak
Jan 2022 – Present | Mountain View, California, United States

### Graduate Research Assistant @ North Carolina State University
Jan 2018 – Jan 2021 | Raleigh-Durham, North Carolina Area
- Evolutionary Algorithms for Hyper-parameter Optimization: Proposed and developed a hyperparameter optimization framework calledOIL(Optimized Inductive Learning), where evolutionary algorithms (e.g. Differential Evolution and NSGA-II) are integrated to supercharge software analytic tasks. OIL was tested on a wide range of optimizers with945 software projects data. Experimental results show that OIL improved the performance of effort estimation in terms of accuracy (won 16 out of 18 cases) and efficiency (reduced runtime from days to hours), respectively.

- Sequential Model Optimization for Software Effort Estimation:Designed a sequential model based method (a.k.a active learning method) named FLASH for the first time in software effort estimation domain to improve software effort estimators. With the constraints of specific computation costs, FLASH can efficiently find good configurations of machine learning methods (e.g. CART) for effort estimations. Overall it can improve the performance of software effort estimation tasks by11%on average in terms of accuracy.

- Project Health Prediction for Open-Source Software:Studied and investigated how predictive methods could help project health prediction. In the study,78,455 months of data from1,628 GitHub projects has been collected. A group of health indicators is defined based on project developing process and industrial domain knowledge. Furthermore, predictive models based on random forests, SVM, and CART have been proposed for the project health prediction. The preliminary results show that the process action on project level can be predicted to a high level of accuracy (10% error rate) with hyperparameter tuning on predicting methods.

### Graduate Teaching Assistant @ North Carolina State University
Jan 2016 – Jan 2018 | Raleigh-Durham, North Carolina Area

### Software Engineer Intern @ NewsBreak
Jan 2021 – Jan 2021 | Mountain View, California, United States
Personalized Local Sports
- Designed and implemented geo-information mapping service API to tag sports news/articles with potential professional and college sports teams. Those tagged articles will be retrieved by downstream local recommendation systems.
- Designed and Implemented doc indexing services of tending sports and Tokyo2020 Olympic for local news recommendation system in NewsBreak App.


## Education
### Doctor of Philosophy - PhD in Computer Science
North Carolina State University

### Master of Science - MS in Computer Science
The University of Texas at Dallas

### Bachelor of Science - BS in Electrical and Electronics Engineering
Nanjing University of Posts and Telecommunications


## Contact & Social
- LinkedIn: https://linkedin.com/in/xiatianpei

---
Source: https://flows.cv/tianpei
JSON Resume: https://flows.cv/tianpei/resume.json
Last updated: 2026-04-11