Hi, I'm Josh!

Current status:
Computer Science and Business at the
University of Pennsylvania

I am a senior at Penn pursuing a dual degree between Penn Engineering and The Wharton School. Previously, I've worked as an undergraduate researcher at Penn Medicine, web developer for the Korean Language Department at Penn, teaching assistant at Penn Engineering (ENM 3750), data scientist intern at the CDC, software engineer intern at Principal Financial Group, and data scientist intern at Meta. I am currently a teaching assistant at Wharton (STAT 4300)!

My Experience

Here's what I've done professionaly so far!

Data Scientist Intern @ Meta

I worked on monetization research and feature innovation for Facebook Pages mainly in SQL, helping unlock scalable revenue streams and boost engagement for over 500M businesses worldwide through tagging and targeted notifications.

Collaborating with data engineers and scientists on query optimization and data pipeline design, I launched an internal product health dashboard that tracked active users, churn, and revenue.

I also partnered closely with product and engineering teams on critical analyses, predicting incremental active user gains for new features and ensuring over 95% confidence in A/B test outcomes.

Software Engineer Intern @ Principal Financial Group

I worked on a client dashboard for individuals to enroll in a robo-investment service based on their risk aversion. On the frontend, I worked with Next.js in TypeScript React to improve web accessibility. For the backend, I implemented API calls in Java that interact with a NoSQL database — all within Spring Boot microservices.

During the company's intern hackathon, I assumed the role of technical lead for my team. We built a React web app that automates business task assignments, using AWS (Lambda, API Gateway, S3) and Llama 3 endpoints.

Data Scientist Intern @ CDC

I created programs in R that analyze which characteristics of labs or chemical analytes affect lab performance in the mandatory inspection tests conducted by the CDC. Here, I was able to learn and hone my skills in data engineering, statistical analysis, and data visualization.

Teaching Assistant @ Penn

I hold weekly recitations to review material with students, grade assignments, and conduct office hours to provide help with Python/R homework for statistics (STAT 4300) and data science (ENM 3750) classes.

Web Developer @ Penn

I designed web-books in HTML/CSS for the Korean Language Department's text book series
("You Speak Korean!").

Undergraduate Researcher @ Penn Medicine

I learned about machine learning using Python libraries like Tensorflow, and Seaborn. With this knowledge, I tested existing machine learning models and consolidated electronic/physical patient data entries.

Portfolio

Projects made with passion - click project names for Github repository!

Retail Car Price Prediction Program

  • This application analyzes 55,000+ data entries of car sale history and predicts car prices based on make year, model, odometer readings, etc.
  • Machine learning models such as Linear Regression, Random Forest, and Gradient Boosting were used. Feature engineering and fine-tuning was performed as well using one-hot encoded PCA and GridSearchCV.

Robot Compatibility Matching App

  • This Android App programmed in Java was used in the FIRST Robotics Competition to collect real-time data input that is used to assess compatibility of a team's robot with another team. SQLite was also incorporated to organize the inputs and produce conclusions from data analysis.

Bioinformatics Toolkit

  • This program illustrates the DNA transcription/translation process through a graphic user interface coded in Python (Tkinter).