Coinbase, Engineering
Institutional Crypto Financing
Shot on a DJI Mavic Mini.
I’m currently a SWE intern at Coinbase, where I work on institutional crypto financing. Previously, I built ML models for signals intelligence and developed energy trading tools. I’m a rising senior at Columbia University, studying math and computer science.
I enjoy building: whether it’s scalable software, ML models, mathematical simulations, woodworking projects, or essays.Reveal Resume
Industry Experience
Scale AI, Technical Advisor
Taught state-of-the-art AI models how to solve complex algorithmic problems.
Expedition Technology, ML Engineering
Worked on computer vision-based RF signal classification. Built and trained a hybrid Mamba architecture model for sequence modeling.
Axpo, Engineering
Built internal tools for energy trading, including automated time series data pipelines and a bot to track and annotate intraday portfolio changes.
Daylight, Engineering
Integrated Daylight's reading app with Zotero’s 7.5M users, enabling access, editing, and upload with version control and deduplication.
Research and Projects
FlareInsure
Built a smart contract trading platform for rainfall insurance with a decentralized, blockchain marketplace for real-world data verification. Won two prizes at ETH Oxford and secured the first dozen waitlist sign-ups within the first week.
GitInsight
Built an AI onboarding tool that lets developers ask natural-language and voice questions about any public GitHub repository.
Containerized with Docker and integrated repo parsing, embeddings indexing, and convo retrieval to deliver <2s responses.
Mathematical Contest in Modeling (MCM) Outstanding Winner
Built a spatial-temporal differential equations model to simulate plant biome evolution under drought cycles, using randomized rainfall and seeding algorithms. Ran large-scale simulations with millions of data points. Our paper won the MAA award and was named Outstanding Winner (top 6 of 10,000+ teams) at the International MCM. Paper accessed here.
Divide and Conquer: Multi-model Approach to Biking Infrastructure
To practive for the MCM, our team also built an optimization model to identify NYC zip codes which would benefit the most from bike land investment based on maximal usage and community benefits. Paper accessed here.
Polyhymnia.ai
As a musician, I built the backend of Polyhymnia to generate unlimited original sheet music using AI and Markov Chains, helping early-intermediate players practice sight-reading. The app uses the Needleman-Wunsch algorithm to assess student recordings and adapt future exercises based on performance. Github Repo
Computer Vision Object Identifier
Through the Inspirit AI summer program, I compared traditional neural network architecture with that of CNNs and implemented transfer learning using VGG16, ultimately devloping an image recognition algorithm using TensorFlow to identify cars and people in videos from car windshields.
Income Tax Simulator
An educational simulation on income taxes which allows users to compare tax policies in several countries, estimate income taxes given a user’s salary, and gain a better understanding of tax policy formation through thought-provoking situational studies.
Hobbies
Photography and Videography
I am also an avid photographer and videographer in my free time and have previously worked gigs for in restaurants, events, and real estate. Here's a sample drone video a friend and I made of Princeton's campus.
Woodworking
My passion for creating doesn’t just stop at software projects but also translates to real world, where I have spent the past summer learning and practicing my woodworking skills. All of my projects are made by hand with nothing more than a whittling knife. Here are some of my favorite pieces.
Writing
I believe that the cognition and reflection inherent in the constructive and original nature of writing crowns it as the ultimate form of expressing ideas. I write every once in a while on Substack. Here's a recent piece: The Philosophy Behind Gifts. Older essays like “Unconscious Bias: The Power and Risks of Societal Narratives”, can be found on Medium.
Contact
Questions, comments or thoughts? You can reach me at pmy2105[at]columbia.edu.