Viola Xu profile picture

Hello, I'm

Viola Xu

CS 2026 Undergrad

My LinkedIn profile My Github profile

Get To Know More

About Me

Experience icon

Experience

2 SDE Internships & 1 Remote
Interested in Machine Learning

Education icon

Education

B.S Computer Science and Economics
Johns Hopkins University


I am a Computer Science undergraduate with experience as a software development intern and a strong focus on frontend development and machine learning integrated app development 👩🏻‍💻.
I have a deep interest in artificial intelligence and natural language processing, and outside of tech, I'm also a passionate nail artist 💅!

Arrow icon

Browse My Recent

Projects

Choose a project
Project 1

ZigZag AI Agent

Developed Livestack, a Realtime AI App Framework, which can easily combine and implement any AI agents.

Key features:

  • Implemented a Discord webcrawler bot that parses for all historical and real-time messages.
  • Integrated the bot with speech app using the framework.
  • Enabled GenAI (Claude) to summarize and update based on real-time speech and Discord conversations.
  • Displayed results on meeting screens for easy access and collaboration.

ZigZag AI Agent
Project 1

Pathogen Analysis Platform

Developed a comprehensive hospital large-screen display module for pathogen data analysis, management, and alert platform.

Project 2

MCI Detector By Gait Analysis

Developed an automated React App System for detecting senior mild cognitive impairment by analyzing gait.

Key features:

  • Using mediapipe and openCV to analyze gait gesture and velocity of the filmed video.
  • Implemented a camera calibration algorithm using a chessboard collection calibration with openCV and 3Dto2d remapping algorithm for image comparation; Allowing for easy and general use of any camera in common daily scenarios.

Project 3

QMastery Pipeline

Developed a QMastery pipeline for enhancing LLMs performance using self-generated question augmentation to solve the problem of limited training data resources

Key features:

  • Enabling self-generating 5k and more data based on 100 seed data, and enhanced models performance by fine-tuning on the generated data.
  • Achieved 10% improvements in the fine-tuned LLM models' accuracy for SAT-Math, GSM8K (grade level math), and Aqua-rat (graduate level math) datasets, demonstrating the efficacy of the novel data augmentation strategy.

Arrow icon

Explore My

Experience

Languages

Experience icon

HTML CSS

Experience icon

TypeScript

Experience icon

JavaScript

Experience icon

Python

Experience icon

Pytorch

Experience icon

React

Experience icon

Vue3

Experience icon

SQL

Experience icon

C++

Certifications & Skills

Experience icon

AWS Cloud Practitioner

Experience icon

Node.JS

Experience icon

Git

Experience icon

MongoDB

Experience icon

mySQL

Experience icon

Docker

Arrow icon

Get in Touch

Contact Me