software engineer
iOS Development Projects
bookBuzz
-
This project was designed as an exploration of UX/UI design and IOS developement
-
Serves as a social media application for readers
-
Users are able to post reviews and engage with other users via comment sections, likes, and follows
-
Gesture implementation and API integration are included
-
Programmed in Swift

Track It
-
A mobile application developed for young adults to track their spending and improve their financial literacy
-
Users can view the time and place of their purchases via a map
-
Track it allows users to add friends and view their purchases to enhance financial accountability and financial awareness
-
Programmed in Swift
-
Designed in Figma
.png)
Fullstack Software Projects
Striking Vipers
-
An exploration of JavaScript, CSS, HTML, SQLite AWS, and cloud deployment
-
A website-based educational game to aid low-income students in learning how to program in the programming language of Python
-
Incorporated integration testing, and unit testing
-
Developed a REST API with Swagger documentation
Smart Store
-
An exploration of UX/UI, software engineering technical designs, and unit testing
-
Proposed for a smart store software system to fully automate the grocery store experience using advanced technology
-
Developed in Java using Intellij
-
Created via the use of Figma, Swagger, SonarQube, and Springboot
Machine Learning/Artificial Intelligence Projects
Level Data - Student Proficiency Model
-
Developed for the company Level Data using Python, Pandas, Scikit-learn, and statistical modeling
-
A supervised machine learning project using anonymized K–12 student data to predict academic proficiency
-
Standardized test scores with z-score and b-score transformations
-
Trained and evaluated 144 logistic regression and decision tree models across school levels and gender
-
Analyzed model performance using accuracy metrics, confusion matrices, and entropy
-
Addressed data cleaning, normalization, and ethical considerations around bias and privacy
ADHD and Sex Prediction Models
-
Built Neural Network and Logistic Regression models to predict ADHD and sex from brain imaging and socio-demographic data
-
Implemented data preprocessing techniques, including handling missing values, categorical encoding, and class imbalance correction
-
Optimized Neural Network hyperparameters (layers, learning rate, batch size) to achieve 72% accuracy, outperforming traditional models
-
Developed for the WiDS Datathon 2025, a global data science competition focused on advancing women's brain health research.