Data Science student @ UC San Diego — building ML systems & products people actually use.
I turn data into things that ship: from 95%-accuracy precision-ag models to live web apps like GradeHQ and Cut. I love the spot where machine learning meets clean, fast product design.
>>> from yashmit import Builder
dev = Builder(
role = "Data Scientist",
school = "UC San Diego",
focus = ["ML", "Data Viz"],
shipping = True,
)
dev.build() # → ideas that ship 🚀I'm a Data Science student who likes shipping, not just analyzing.
At UC San Diego I focus on machine learning and data visualization, but my favorite work happens when a model leaves the notebook and becomes something real — a mobile app, a research paper, a live website. I've taken projects from raw data all the way to the App Store and production web.
That path runs from precision-agriculture research hitting 95% accuracy, to a personal-finance app for fellow Tritons, to an AR gesture-recognition system with sub-100ms latency. Outside of code, I'm an Eagle Scout who led a robotics team to the world championship and ran two student clubs.
Research, open source, and real products — selected roles where the work shipped and the numbers moved.
La Jolla, CA
Remote
Egypt
A stack that spans machine learning, full-stack engineering, and the hardware where bits meet the real world.
Live products, ML research, and hardware experiments — each with a link so you can dig in yourself.
Mobile-first personal finance app for UCSD students — budgeting, expense tracking, goals, and AI insights, backed by REST APIs and a PostgreSQL schema with automated triggers.
ML-powered precision-agriculture platform reaching 95% accuracy across 100K+ weather and soil data points. The research became a cross-platform app with seasonal crop calendars and yield predictions, published to the App Store.
AR-inspired gesture and ASL recognition system enabling IoT control with sub-100ms latency. Combines computer vision with a Bluetooth + microcontroller stack and custom 3D-printed enclosures.
Smart waste bins that use AI to classify and sort trash automatically — pairing an Arduino hardware build with a vision model to push sustainability at the point of disposal.
A food-waste tracker for dining halls that measures and visualizes what gets thrown out, giving operators the data they need to cut waste at the source.
A simple, accessible way for people to report crime in their community — lowering the friction between witnessing something and getting it on record.
I build teams and communities the same way I build software — with ownership and measurable results.
Boy Scouts of America
Aug 2021 — Present
President
Aug 2023 — May 2025
President
Aug 2022 — May 2025
I'm open to Summer 2026 internships and collaborations in data science, ML, and full-stack — and I take on freelance work too. Need a website, app, or any digital build? You can hire me directly on Fiverr. The fastest way to reach me is email; I reply quickly.