Education

• B.A. in Mathematics, University of Pennsylvania, 2019–2023
• M.S.E. in Data Science, University of Pennsylvania, 2021–2023
• GPA: 3.9/4.0
• Notable courses: Machine Learning, Computer Vision, Theory of Machine Learning, Game Theory, Probability Theory

Work experience

• Spring 2022: Applied Scientist Intern at Amazon
  • Worked on Amazon Help Search Q&A System to expand English IR model to multiligual IR model
  • Built data pipeline including scraping, annotation collection, and data augmentation on millions of datapoints
  • Improved MRR from 22% to 45% with the same runtime by performing knowledge distillation on multilingual-BERT model
  • Mentor: Olive Qin
  • Manager: Rajesh Kamma
• Summer 2022: Machine Learning Engineer Intern at Roblox
  • Worked on Account Security team to use username feature to improve bot detection
  • Designed a scalable and distributed text mining algorithm that achieved 90%+ F1 score
  • Implemented the algorithm and its data processing, hyperparameter tuning using Spark, SQL, Hive, Hadoop, Airflow, Kubeflow
  • Implemented Markov chain-based gibberish detection
  • Mentor: Derek Farren, Younes Abouelnagah
  • Manager: Luke Fu

Skills

• Python: Pytorch, HuggingFace, CUDA, OpenCV, PySpark, Selenium, Multiprocessing, Regex
• Big Data: Spark, SQL, Hive, Hadoop, Airflow, HPC, Slurm
• Others: Linux, Github (version control), AWS, GCP