Hi, I'm Hershraj. I'm pursuing a Bachelor's degree in EECS at UC Berkeley. I'm currently working as a machine learning engineering intern at Property Finder.
My research at BAIR focuses on LLM guided program synthesis and interpretable machine learning. My prior work involved timeseries forecasting and PINNs.
Feel free to reach out if you'd like to chat about research or collaboration!
Projects
DreamPy: Python rewrite of the Dreamcoder framework.
ThrowdownTV: Low-latency RTMP live video streaming platform (React, Express, Rust, Typescript).
Formify: Computer vision tool to convert photos of tables into accurate CSV files.
Education
University of California, Berkeley (2023–2027)
B.S. in Electrical Engineering & Computer Science
GPA: 3.77/4.00
Moorpark College [Dual Enrollement] (2019–2023)
Honors (Top 25% GPA)
Research
LLM-guided program synthesis & interpretable ML at BAIR under Matteo Guarrera & Carlo Bosio.
Multihorizon timeseries forecasting via deep learning and attention.
Physics-informed neural networks for PDE solvers.
Prior work on neural cost computation during decision-making at the Wilbrecht Lab.
Teaching
Senior mentor for CS 70 and junior mentor for CS 61A, CS 70 (CSM).
