Hi, I'm Advaith Malka

I'm a junior at Virginia Tech pursuing a BS in Computer Science focusing on machine learning and data science. Welcome to my personal website, where you can explore my work and learn more about what I do.

Projects

Project

Traffic Simulator

Real-time 3D multi-agent traffic simulator using the Improved Intelligent Driver Model and MOBIL lane-change logic to surface emergent behavior like phantom jams.

4/26/26

Project

StructAI

Fine-tuned version of Meta LLaMA that can generate real-time visualizations of data structures.

5/17/25

Project

NC Ratio Calculator

ML model that calculates the Nucleus-Cytoplasm ratio of a cell image.

4/1/25

Project

BioSegment

Utilizes Computer Vision to segment Mitochondira and Cristae from EM images.

3/28/25

Project

Squat Form Analyzer

Uses openCV + Mediapipe to analyze the depth of your squat.

7/29/24

Project

Cop Classifier

Classifies cars as police vehicles or regular traffic. Can be used in traffic signals to detect cop cars.

7/16/24

Project

MediCord

An app that transcribes and summarizes audio files quickly and efficiently for patient use after doctor visits.

4/11/21

Project

SuperChat

A realtime chat app built for the future.

12/19/20

Project

JobRecover

A web app made for HackTJ 7.5 and designed to connect employers to the unemployed, during difficult times. Thanks to Sritan and Nithil for making this project possible.

12/13/20

Project

DevMedia

A social media app built for developers, by developers.

11/19/20

Project

Chess AI

Play chess against an AI right in your browser!

10/7/20

Who am I?

Hi! I’m Advaith Malka, a Computer Science junior at Virginia Tech focused on machine learning and AI systems. I've built everything from fine-tuned LLMs to computer vision pipelines, and I've shipped production AI tools at Collins Aerospace (RTX). When I’m not coding, you can find me on the court playing basketball, pickleball, or tennis.

Advaith Malka

Experience

Undergraduate Research Assistant

ROLE Lab - Virginia Tech

August 2025 - Present

  • Integrated RAG with special uncertainty tokens, reducing unnecessary LLM retrieval by ~30%.
  • Built a RAG evaluation pipeline using vLLM and ElasticSearch to benchmark LLMs on 30K+ queries.
  • Automated end-to-end data processing pipelines to standardize 6 major academic datasets for experimentation.

Cybersecurity and AI Intern

Collins Aerospace - RTX Corporation

May 2025 - August 2025

  • Developed an AI agent using RAG to generate context-aware code, accelerating development by ~70%.
  • Containerized the RAG agent with Docker, improving scalability and ease of deployment.
  • Researched and built cybersecurity tools to optimize fuzzing pipelines and enhance vulnerability detection.

Undergraduate Research Assistant

EEG2Text - Virginia Tech

February 2025 - June 2025

  • Maintained codebase for EEG2Text research paper by Professor Wang and colleagues.
  • Refactored and optimized 2000+ lines of code for improved readability and modularity.
  • Identified and resolved 5+ issues by debugging and writing testing scripts using multimodal EEG data.

Skills

Languages

Python

Java

C

HTML

CSS

JavaScript

SQL

Frameworks & Libraries

PyTorch

NumPy

Pandas

file_type_jsp

JakartaEE

React

Django

Node.js

MongoDB

SASS

Tailwind CSS

Get in Touch