I'm a researcher in materials informatics, with a focus in applied machine learning. Also, I am a strong believer in the open science movement and an advocate for science outreach organizations.
I enjoy cooking, martial arts (Taekwondo), listening to and playing music, reading sci-fi/fantasy novels, and playing video games. I'm an alumnus of the University of Guelph with a BSc in Nanoscience; currently, I'm working on my PhD in Materials Science at MIT in the Olivetti Group, as a part of the Synthesis Project.
Most of my time is spent working on my PhD thesis, which focuses on a new approach for predictive materials synthesis using various ML techniques, including convolutional / recurrent neural nets, generative models, and domain-specific representation learning. The goal of this project is to further accelerate the design of novel inorganic materials - particularly those with useful properties (e.g., for energy-related devices).
My efforts on this project range from full-stack engineering to scientific writing, and my passion is in the application of machine learning models. I'm especially interested in learned data representations, physically-meaningful and interpretable model predictions, robustly evaluating generative models, and adapting NLP algorithms to domain-specific text.
Over the past several years, I've worked on a variety of projects spanning the fields of experimental physics, computational materials science, materials informatics, Python modules, machine learning consulting, and battery electrode design. My formal training is in nanoscience, physics, and materials science - but my focus has gradually shifted from inorganic materials to broader domains.