Skip to content
View Joyshah62's full-sized avatar

Block or report Joyshah62

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Joyshah62/README.md

Joy Shah — M.S. Computer Science @ Rutgers University

Website LinkedIn Email Repositories


About

I build machine learning systems that leave the notebook. Currently an M.S. Computer Science student at Rutgers University (expected 2027), where I also run recitations for 100+ undergraduates in CS336.

Most of my work sits at the seam between research and infrastructure: retrieval pipelines that have to return the right document in under a second, classifiers whose predictions someone has to defend, and services that need to still be up on Monday. I have an IEEE publication on biometric security, and my internships shipped ML features to production rather than to a slide deck.

Currently: building a mock-interview platform — a RAG pipeline that matches interview questions to a job description and résumé, backed by a scraping and deduplication stack I wrote from scratch.

Looking for: Summer 2026 SWE / AI-ML internships on teams working with LLM applications, NLP systems, or ML infrastructure.


Focus

Focus areas: retrieval and LLM systems, NLP and interpretability, production engineering


Toolkit

Languages Python Java JavaScript C++ SQL Kotlin
ML / NLP PyTorch TensorFlow scikit-learn Hugging Face LangChain NumPy pandas
Backend & web FastAPI Flask Node.js React
Data stores PostgreSQL MySQL MongoDB DynamoDB Elasticsearch
Infra AWS Docker Git Linux GitHub Actions

Activity

GitHub stats Top languages


I train models to catch bad actors and bad code. Both respond well to proper validation.

Pinned Loading

  1. E-Library E-Library Public

    JavaScript 3 2

  2. Web-Application-Firewall-using-AI-ML Web-Application-Firewall-using-AI-ML Public

    HTML