Skip to content
View Jeremytsai6987's full-sized avatar

Highlights

  • Pro

Block or report Jeremytsai6987

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Jeremytsai6987/README.md

Hi, I'm Ya-Wei (Jeremy) Tsai 👋

GIF

Portfolio-CLICK ME
  • I'm a highly motivated M.S. in Computer Science candidate at The University of Chicago, specializing in Cloud Computing, Machine Learning, Data Analytics, and Distributed Systems.
  • My passion lies in leveraging cutting-edge technologies to solve complex problems and drive innovative solutions.
Connect with me on LinkedIn Connect with me on LinkedIn

Education:

  • The University of Chicago (Chicago, IL)

    • M.S. in Computer Science, March 2025 (Expected)
    • Specialized in Cloud Computing, Machine Learning, Data Analytics, and Distributed Systems
  • National Taiwan University (NTU) (Taipei, Taiwan)

    • B.A. in Economics and Double Major in Political Science, January 2022
    • Concentrated in Statistics, Econometrics, and Machine Learning
  • Lund University (LU) (Lund, Sweden)

    • Exchange Program in Social Science, January 2022

Professional Experience:

  • P.LEAGUE+ (Taipei, Taiwan)

    • Data Analyst, September 2022 - July 2023
    • Orchestrated the development of comprehensive player and referee datasets employing Synergy Stats and Python, yielding pivotal insights for tactical and strategic decision-making by teams, league authorities, and media representatives.
    • Executed sophisticated K-means clustering to analyze player performance metrics and team dynamics; utilized Streamlit to create interactive visualizations, enhancing stakeholder understanding and engagement, and applied Excel for systematic data management, supporting nuanced analytical narratives.
    • Conducted behavioral data analysis to distill customer trends and preferences, utilizing Python for data manipulation and Excel for data visualization, thereby informing customer engagement strategies and operational enhancements.
    • Designed and managed a robust data pipeline using Python to streamline the aggregation and preprocessing of complex datasets, leading to a more efficient workflow and timely insights for strategic initiatives.
  • Fermilab (Data Science Clinic) (Chicago, IL)

    • Data Science Intern, March 2024 – June 2024
    • Enhanced Graph Neural Networks to improve neutrino detection in Liquid Argon Time Projection Chamber systems, increasing detection efficiency and accuracy.
    • Implemented a sawtooth mechanism and residual connections in neural networks, resulting in a 3% increase in model accuracy and a 5% improvement in overall performance.
    • Leveraged Python and PyTorch for model development and optimization, ensuring robust and reliable data analysis processes.
    • Collaborated with a team of scientists and data experts, contributing to groundbreaking research in particle physics and data science.
    • Analyzed complex data sets to derive meaningful insights, supporting the development of advanced detection methods and contributing to the broader scientific goals of Fermilab.
  • The Climate Extremes Theory and Data (CeTD) Group – The University of Chicago (Chicago, IL)

    • Research Assistant, June 2024 - Present
    • Processed data pipeline for efficient handling of large scientific datasets.
    • Developed a parallel IO DataLoader utilizing dask and xarray for improved data processing performance.
    • Adapted and modified AI weather models to enhance forecast accuracy for predicting the Asian monsoon.
    • Contributed to projects aimed at assisting farmers in India by providing more reliable weather forecasts.

Projects:

  • Buy Earth a Coffee Application (March 2024 - June 2024)

    • Implemented back-end functionalities in Node.js with MongoDB for data management, using Mongoose for database schema creation and data interaction.
    • Integrated AWS S3 for file storage, handling file uploads and secure storage with public access configurations.
    • Configured secure user authentication and session management using Next-Auth, enhancing application security and user experience.
    • Utilized React for front-end development, enhancing UI with custom components and managing state with hooks.
  • NuGraph: a Graph Neural Network (GNN) for Neutrino Physics Event Reconstruction (Partnering with Fermi Lab, March 2024 - June 2024)

    • Advanced NuGraph3 GNN architecture, optimizing data aggregation and message-passing for enhanced event-level predictions.
    • Implemented a sawtooth mechanism for sequential node embedding updates, refining model accuracy and performance.
    • Applied residual connections in NuGraph3, boosting robustness and feature refinement across iterative message-passing.
    • Streamlined data pipelines with Python, enabling efficient data handling and supporting advanced analytical capabilities.
  • Genomic Annotations Service (January 2024 - March 2024)

    • Led the design and development of a Genomic Annotations Service, a web service for gene data analysis utilizing Flask, Globus, and AWS cloud technologies including S3, EC2, SQS/SNS, DynamoDB, Lambda, and Step Machines.
    • Built RESTful APIs with JavaScript and Python, managing data workflows and service integration to provide a robust user experience.
  • Generative AI Idea Validator for Circular Economy (January 2024)

    • Pioneered the design and deployment of a cutting-edge AI-driven validation tool using OpenAI GPT-4 to analyze and categorize concepts within the circular economy sector. The tool is engineered to autonomously produce detailed reports that evaluate the sustainability, commercial potential, and innovative aspects of new ideas.
    • Integrated Retrieval-Augmented Generation (RAG) with GPT-4 to enhance the AI's ability to fuse retrieved information with generated content, ensuring the production of highly accurate and contextually relevant sustainability assessments.

Languages and Tools:

📊 this week i spent my time on:

No activity tracked

Pinned Loading

  1. brianchanbc/GenAIEarthHack brianchanbc/GenAIEarthHack Public

    AI EarthHack - Generative AI Hackathon - Chicago Machine

    Python 1

  2. PawClock-iOS-Application PawClock-iOS-Application Public

    An application that discover a delightful way to organize your day with PawClock, your go-to app for scheduling meals and pet activities seamlessly integrated with engaging gaming experiences. PawC…

    Swift

  3. Reinforcement-Learning Reinforcement-Learning Public

    Jupyter Notebook

  4. BertQA BertQA Public

    Jupyter Notebook

  5. HellKitchen-Game HellKitchen-Game Public

    Java

  6. shell shell Public

    A project that demonstrates a deep understanding of systems programming and operating system concepts. In this implementation, the program acts as an interface for the user to interact with the ope…

    C