Avery Pai

I'm

About

Hello there, I am Ya Ting Pai, people usually call me Avery.

I’m currently applying to Computer Science programs to solidify my knowledge in information retrieval.

Machine Learning Engineer & Critical Thinker

My academic background spans Computer Science, Statistics, and Finance, empowering me to tackle problems with a multifaceted perspective. This breadth of knowledge positions me to actively contribute to class discussions, particularly in addressing complex issues.

My professional journey has further augmented these skills, with two years of experience in Machine Learning, focusing on enhancing search functionalities using language models.

The practical skills I've gained in software engineering, complemented by my master's degree in Statistics from National Yang Ming Chiao Tung University (NYCU), have deepened my understanding of both theoretical and applied aspects in computer science.

My career has underscored the value of knowledge in computer systems and social computing, key to developing efficient and robust search systems.

- Avery

Resume

Keywords: Python, Elasticsearch, Google Cloud Platform, Git, Docker, Bash, Linux

Professional Experience

Senior Machine Learning Engineer

2023 - Present

iKala, Taipei, Taiwan

  • Furnished a comprehensive Ads detection model as a package, supporting 6 languages and reaching 4,000+ users in the Chrome extension 'Influencer Analytics by KOL Radar'
  • Trained retrieval models to outperform BM25 by approximately 5% on NDCG@100
  • Improved system latency by 64% by decreasing the encoder dimension
  • Conducted surveys on fifteen research papers as part of a search engine proposal, contributing to the redesign of the Elasticsearch schema in collaboration with the backend team for the development of upcoming components
  • Delivered two presentations for a recommendation system project, outlining the development, features, and benefits to 197 stakeholders

Machine Learning Engineer

2021 - 2023

iKala, Taipei, Taiwan

  • Championed the development of a multilingual recommendation system from inception, utilizing Python and object-oriented programming principles, while also crafting a user-friendly Streamlit interface. Highlighted as a pivotal achievement in an external stakeholder meeting
  • Engineered and deployed two search functions utilizing Elasticsearch's semantic and vector search features: one for similar KOLs and another for related posts
  • Conducted twelve experiments on locality-sensitive hashing, DBSCAN, Birch, and K-Means for extracting features from KOL’s posts
  • Streamlined five model pipelines by extracting social media posts from Google BigQuery and seamlessly transferring models to Google Cloud Storage
  • Mentored two interns in labeling 10,000+ text training data in Japanese and Chinese

Academic Experience

Teaching Assistant

2021

NYCU, Hsinchu, Taiwan

  • Collaborated with the course instructors to develop and modify course content and materials to enhance student engagement and understanding
  • Graded assignments and exams, providing timely feedback to 35 students.

Research Assistant

2019 - 2020

Academia sinica, Taipei, Taiwan

  • Revamped and reexamined clustering algorithm in Python, which outperformed Spectral clustering algorithm by 3% on the Karate club network dataset

Education

Master in Statistics

2020 - 2021

NYCU, Hsinchu, Taiwan

  • GPA: 4.0/4.0
  • Thesis topic: A Deep Learning Method of Genetic Testing for Lung Cancer

Bachelor in Business Administration

2014 - 2019

National Tsing Hua University, Hsinchu, Taiwan

  • GPA: 3.65/4.0
  • Major: Computer Science and Finance

Exchange Student

2018

Shanghai Jiao Tong University, Shanghai, China

Related courses

Computer Science related

48 credits
  • Text mining
  • Machine Learning
  • Deep Learning
  • Introduction to Programming (I)
  • Introduction to Programming (II)
  • Discrete Mathematics
  • Digital Logic Design
  • Operating Systems
  • Computer Architecture
  • Design and Analysis of Algorithms
  • Linear Algebra
  • Data Structures
  • Introduction to Computer Networks
  • Hardware Design and Lab
  • Algorithms

Math/Statistics related

40 credits
  • Causal inference
  • Multivariate Analysis
  • Statistical Computing
  • Time Series
  • Intro to Data Science
  • Mathematical Statistics
  • Engineering Mathematics
  • Mathematical Statistics (I)(II)
  • Business Analytics Using Computational Statistics
  • Calculus (I)(II)
  • Statistics (I)

Facts

With these experiences, I am keen to expand my expertise in retrieval algorithms and systems.
I am confident in my preparedness for the advanced courses offered in your program.

Credits of CS courses

Years of Work experience

Credits of Math/Stat courses

Years of research experience