Hi, I'm Jeffrey.

I'm a junior at MIT studying computer science and engineering. I'm currently a Software Development Engineering intern at Amazon Web Services, working on serverless containers with the Fargate Placement team, and a part-time developer at Vibrantec, a startup building a cross-platform health and wellness app.

I'm interested in deep learning across computer vision, NLP, and reasoning systems. On the engineering side, I'm passionate about AI automation -- using agents to streamline complex workflows and eliminate repetitive tasks. I've built automated agents using LangChain and worked on robotic automation at the MIT Media Lab.

I serve as an advisor to The Silicon Project, a nonprofit donating electronics to underserved communities, where I previously led the IT department. Before transitioning to software, I researched molecular pharmacology at the Grimm Lab at Memorial Sloan Kettering Cancer Center, investigating statin-based approaches to improve nanomedicine delivery for cancer treatment.

Outside of tech, I'm passionate about working out, meal prep, movies, reading, basketball, and hiking.

Here are some tools I've used in previous roles and projects. Hover over each item to learn more about my development experience.

Java

Python

Javascript

Typescript

React.js

Next.js

Tailwind

Express

FastAPI

Prisma

Neon

Dart

Flutter

Maya

Vercel

Below are some projects I've worked on over the years. Hover over project images for live demos and over project details for more information.

View demo

Casava

A sublet search platform for college students that aggregates listings from Facebook Marketplace, Craigslist, and Airbnb into one interface. Uses AI and RAG to recommend listings based on user preferences, with chat functionality to find ideal matches. For sellers, the platform offers verified listing capabilities with built-in scam detection, in-app messaging, and payment processing to ensure secure transactions. Project is still ongoing and have received $1500 in pre-seed funding by MIT Sandbox.

Next.jsTailwindExpressNeonPrismaGemini

View demo

Jeffrey's MacBook

A personal website with a MacOS-style interface featuring a dock menu and apps like Finder, Notes, Spotify, Photos, Email, and Messages. Navigate to the Messages app to chat with an AI version of myself.

Next.jsTailwindGemini

View source

View demo

MarketOwl

An AI negotiation assistant for Facebook Marketplace that analyzes listings and seller messages to help you get better deals. Just paste a listing URL and get personalized negotiation messages optimized for that specific seller.

Next.jsTailwindFastAPIOllamaLlamaModal

View source

Visage

A video editor that automatically creates highlight montages by syncing audio beat drops with key moments in your footage. Upload your clips (basketball, gaming, etc.) and audio - the algorithm handles the editing to create seamless highlight reels.

Next.jsTailwindFirebaseFFmpeg

View source

View demo

SciClubs

A mobile app for students to browse school clubs, join activities, and track their schedules through a personalized calendar. Club leaders can take attendance and make announcements. Built as my introduction to full-stack development with authentication and database features, presented at the Bronx Borough Science Expo.

FlutterDartFirebase

View source

View demo

Bronx Science NHS Website

The official site for the Bronx Science National Honor Society (NHS) provides details on the application process, member responsibilities, and tutoring forms. Created as my first web development project, it is now used and maintained by student leaders at Bronx Science.

React.jsTailwind

View source

View demo

Improve Nanomedicine for Cancer Project

Wet lab research investigating how statins can reduce nanoparticle uptake in macrophages to enhance cancer treatment effectiveness. Developed skills in cell culture, flow cytometry, and western blot analysis.

ExcelPrism

View source

View demo

3D Animation of Cancer

A fully animated project created in Autodesk Maya and edited in Adobe Premiere. All 3D models were built and rendered in Maya, with Python scripts used to automate repetitive tasks like randomizing DNA helix and cell positions. Created as a final project for MITES Semester 2023.

PythonMaya

Find out what I'm listening to on Spotify below.