Developed 22+ REST API endpoints with Flask and SQL CRUD operations with PostgreSQL.
Managed and deployed cloud instances on AWS EC2 / ECS
Ensured 80%+ test coverage through unit and integration tests
Waterloo Data Visualization Group (WatVis)
Jul. 2021 — Current
Undergraduate Research Assistant (ML/Backend)
Waterloo, ON
Hosted GauGAN and Neural Style Transfer inference models on Flask server with GCP instance
Designed Go backend to allow real-time collaborative drawing
Built frontend with React Native web/mobile app
App adopted by art therapists + general users
Waterloo Data Visualization Group (WatVis)
Jan — Aug. 2021
Undergraduate Research Assistant (ML/Backend)
Waterloo, ON
Generated Doc2Vec embeddings for RNN and classification models
Deployed Flask backend to host CodeBERT model inference and TF-IDF keyword extraction functionalities
Trained LDA models for topic modelling of 86k+ data science notebooks
Software Analysis and Intelligence Lab
Apr. — Sept. 2020
Software Engineering Research Intern
Kingston, ON
Built a robust web crawler to mine a network of 6+ million text articles totalling 109GB in size.
Applied machine learning models (logistic regression, support vector machines) using Python (pandas and scikit-learn) to study 6 million Software Engineering articles.
Implemented multiprocessing techniques to increase feature extraction performance by 8-fold.
Wrote SQL queries on Google BigQuery to assess Medium.com's popularity on Stack Overflow.
Software Analysis and Intelligence Lab
Jul. — Oct. 2019
Software Engineering Research Intern
Kingston, ON
Used R and Python to preprocess and extract 100+ features from 19.3 million messages to study the Stack Overflow chat platform.
Trained logistic regression models on 86K chat rooms
Evaluated models with AUC/ROC, AIC, Wald statistics.