Parth Kotwal

Aspiring Computer Scientist


Parth Kotwal

About Me

Hello, I'm Parth, a Computer Science student at the University of Washington, Seattle, with a fiery passion for machine learning and building tools for my own problems, then scaling them. I’m currently interested in recommendation systems and in evaluating multi-turn agents through my work at the UW Computer Systems Lab.

In my spare time, I enjoy:

Playing the latest FIFA or badminton!
Following my favorite football team FC Barcelona
Reviewing restaurants, cafes, and bakeries on Beli
Expanding my fragrance collection ($n = 10$)

Experience

Machine Learning Researcher

University of Washington Computer Systems Lab • October 2025 - Present

Software Engineer Intern - ML

miniOrange • July 2024 - September 2024

Projects

Olds

Go FastAPI React PostgreSQL + pgvector Docker spaCy

A news site with a recommendation system that tracks both user interactions and content similarity. Inspired by my childhood routine of reading only the newspaper sections that interested me every morning

QueQueue

Django Vue.js Scikit-learn AWS (ECR, EC2, S3, RDS, Cloudfront) Docker PostgreSQL

Django + Vue app to save, restore and recommend Spotify queues. Addresses a personal trauma of losing the ideal Spotify queue on many occasions

Transient Detection with braai CNN

PyTorch CuPy NumPy Scikit-learn

Custom CuPy/NumPy CNN for astrophysical transient detection. Based on the "Real-bogus classification for the Zwicky Transient Facility using deep learning" paper

Model United Nations Northwest SMS Admin

FastAPI JS PostgreSQL Tailwind CSS

FastAPI + Twilio SMS admin for conference announcements and scheduling. Currently used by the largest Model United Nations conferences in the Pacific Northwest

Automated Stellar Classification

Scikit-learn Pandas NumPy Matplotlib

Random-forest-based stellar spectral classifier with high accuracy and interpretability.