Hey, I'm Yash 👋

I build AI systems and study how they break.

I build AI systems and probe how they break — from LLM evaluation pipelines to adversarial machine-learning research. Currently an M.S. Computer Science student at Georgia Tech (AI concentration), researching ML security and building production LLM systems.

Y

A photo of Yash goes here — drop one at public/me/avatar.jpg.

Experience

Where I've been building.

FINRA

May 2026 – Aug 2026

Graduate AI Engineering Intern

Built an automated LLM evaluation pipeline on AWS Bedrock + S3 that raised measured groundedness to 95% across 1,200 internal chats over dense SEC filings.

Georgia Tech

Aug 2025 – Present

ML Security Researcher

Designing an ML attack in PyTorch against a 105-bit iris-based key-derivation scheme, and a modular LangChain + Ollama framework that improved reproducibility of attacks and defenses by 3×.

VeriSign

May 2025 – Aug 2025

Product Engineering Intern

Architected a Spring Boot REST API with Spring Security and token auth that cut a multi-hour manual DNS data process down to sub-5-second automated responses.

Education

M.S. Computer Science — Artificial Intelligence

Georgia Institute of Technology · GPA 4.00 · Dec 2026

B.S. Computer Science — Faculty Honors

Georgia Institute of Technology · GPA 3.96 · Dec 2025

Selected work

Projects I've enjoyed building.