I'm a third year Computer Science student at Oregon State University, specializing in AI and enrolled in the Accelerated Master's Platform (AMP). I want to leverage Artificial Intelligence to build real world applications with meaningful impact. I'm always searching for opportunities to apply my skills to new challenges, projects, and opportunities.

In my free time, I enjoy playing tennis on the OSU Club Tennis team, going on hikes, learning about investing, and playing/watching basketball.

Languages:
               

Technologies/Frameworks:
             

Tools:
   

My personal portfolio, built to showcase my projects, skills, and experience.

Features:

• Built with Next.js, React, and TypeScript with Tailwind CSS for styling.
• Features a full CI/CD pipeline with Git and Vercel for automated build previews and production deployments.
• Uses Sanity.io as a headless CMS to dynamically manage all site content, including projects and skills.

🔗 Live Site 🔗 GitHub Repo ---

A full-stack portal for Oregon State’s BeaverHacks program (team project).

Features:

• Served as the central hub for event registration, team formation, and project submissions for 500+ participants.
• Developed dynamic, role-based dashboards for participants, judges, and organizers using Next.js and TypeScript.
• Implemented a secure back-end using Prisma ORM and PostgreSQL.

A full-stack app that captures and converts audio input into structured text notes.

Features:

• Leverages the Web Speech API for real-time, in-browser voice transcription.
• Responsive user interface built with React.js and a RESTful API powered by Express.js.
• Established a data persistence layer using MongoDB to save, access, and manage user notes.

• AI Stock Market Predictor An application to explore machine learning models for predicting stock market movements.

  Features in development:

  • Ingesting financial data from various APIs (e.g., Alpha Vantage, Yahoo Finance).
  • Training and testing various ML models (e.g., LSTM, ARIMA) with Python.
  • A React-based dashboard for visualizing predictions and model performance.

• LLM-Driven Software Migration Testing the validity of a semi-automated pipeline using LLMs to translate robust, but hard-to-maintain, legacy scientific software (e.g., Fortran) into modern, extensible languages (e.g., C++ or Rust).

Features in development:

• Ingesting and parsing legacy Fortran code from scientific domains (e.g., fluid dynamics, computational physics).
• Using iterative LLM prompts and compiler error feedback to automatically translate and refine code.
• Building an evaluation scaffold to verify correctness (compilation success, semantic equivalence) and measure code quality.
• A human-in-the-loop verification system to allow expert developers to correct, annotate, and approve translations.