ABOUT ME

Machine Learning Intern
Tailbox

Played a pivotal role in the development of foundational machine learning models to help tourists gain a personalized travel experience in any city.

- Trained custom embedding and cross-encoder models that improved RAG pipeline results by 14% and reduced latency 50-fold compared to OpenAI models.
- Fine-tuned Qwen2-1.5B SLM to convert HTML text to structured database entries to reduce reliance on private models and save $20/day per city; optimized inference for 19-fold speedup.
- Wrote a robust Requests & Selenium AWS EC2 scraper that collects Boston tourist events found on Instagram; collected a dataset of 18k+ user-query:activity pairs.

Design Technologist Intern
Amazon

Conceptualized, designed, and implemented an API establishing communication between large language models and the Amazon Alexa infrastructure. LLMs demonstrated chain-of-thought reasoning to utilize Alexa as a tool for solving complex tasks.

- Developed Express.js API to interface custom-trained LLM models and the AlexaEmulator, capable of simulating interactions with specific devices through serial numbers/customer IDs.
- Collaborated with cross-functional teams to gather and synthesize diverse requirements, implementing solutions that aligned with stakeholder needs.
- Presented project to DDG team to enable future use for a larger LLM project slated for presentation at the upcoming 'Demo Crawl' event in Spring 2024.

Machine Learning Researcher
MIT Computer Science and AI Laboratory (CSAIL)

Co-authored a research paper on developing software to modify 3D-printable objects given user instructions, while preserving the objects' functionality. Paper accepted by ACM UIST Conference.

- Implemented the software as a plugin on Blender; backend hosted on AWS EC2 running CLIP on Django framework.
- Automated collection of 3D-model datapoints using Selenium; added 1000+ annotated data points to the model training database.
- Created web UI for model using React, Node.js, and Django; streamlined user experience by providing model- uploading, re-meshing, and stylization on the web.

Software Engineering Intern Relari

Designed and developed an LLM assistant that analyzes financial documents to generate relevant insights and media for financial professionals.

- Implemented REST API using Express.js, integrating the proprietary LLM (trained on user's documents) with a PostgreSQL database to dynamically generate tailored slides.
- Engineered document processing pipeline using NLP, enabling LLM to extract, categorize, and synthesize key financial data from diverse document formats for incorporation with dynamic slide generation.

Software Engineering Intern
Bausch Advanced Technologies

Collaborated with a team to develop an app optimizing workflow efficiency across multiple departments. Leveraged ASP.NET framework (XAML, C#, PostgreSQL)

- Utilized xTuple API and company database to display part availability and work/purchase order retrieval, dramatically reducing human labor time.
- Implemented SolidWorks 3D viewer directly in-app; includes feature tree, missing parts lookup, and printing.

Bachelor's Degree MIT

Computer Science - 4.8/5.0 GPA

Relevant Coursework:

• Computer Science with Python
  Computational Thinking and Data Science
  Fundamentals of Programming
  Low Level Programming with C & Assembly
  Computation Structures
  Operating Systems Engineering
  Algorithms I
  Algorithms II
  Systems Design
  Discrete Math
  Linear Algebra
  Machine Learning

H.S. Scholar Wesleyan University

Attended prestigious program for students to further their education with classes not offered at high school.

High School Diploma Morgan School

Valedictorian - 4.4/4.0 GPA