Hi, I'm Jawaad.I build things people actually use.

I'm a full-stack & AI engineer finishing my MS in Computer Science at Rutgers, shipping production platforms and AI tools people rely on.

Open to SWE & AI/ML rolesBased in New Jersey

Illustrated portrait of Jawaad Jariwala
Scroll

Selected work

Things I've built

All projects on GitHub
01Assistive AI · Award winner

BlindSpot

A real-time assistant that helps blind users find lost items independently — no more waiting on a video call with a stranger. Streams live camera frames through Gemini 2.5 Flash and speaks back clock-position directions ("your keys are at 2 o'clock").

  • FastAPI
  • Gemini 2.5 Flash
  • ElevenLabs TTS
  • Web Speech API
Rutgers Raptor Rise Best Community
Impact Award
out of 50 projects
Hack RUC 2025 2nd Place RAG over verified policy docs
02RAG · Social impact

Fairly

Domestic workers often have no easy way to learn their legal rights. Fairly answers plain-language questions using a RAG pipeline grounded in verified government and policy documents — built on a semantic chunking pipeline that turns messy policy PDFs into clean, retrievable knowledge.

  • FastAPI
  • Next.js
  • Gemini 2.0
  • MongoDB
  • Snowflake
03Full-stack · Master's project

Voltra Fitness

A cross-platform fitness and nutrition app I designed and built end to end — UI/UX included. Offline-first: Expo SQLite is the primary store with background Firestore sync, so it keeps working with no connection. Snap a meal photo and Gemini Vision estimates the macros.

  • React Native
  • Expo
  • FastAPI
  • Firebase
  • Gemini Vision
Architecture Offline-first
sync engine
SQLite primary · Firestore background
BigQuery · Python 43M rows HHI risk across 52 states
04Big data · Analytics

Aramark Procurement Analytics

A cloud-native analysis of 43M+ rows of real procurement data on BigQuery — solo, despite the "group project" label. Found that one distributor controls 54% of US spend, quantified antitrust risk with the Herfindahl-Hirschman Index, and joined NOAA climate data to explain seasonal demand swings.

  • BigQuery
  • Python
  • scikit-learn
  • NOAA data
05Data visualization

AWS EC2 Pricing Landscape

Mapped 318,604 EC2 price points across 1,337 instance types and 104 regions to find out how AWS actually prices compute. Only 6.2% of instance types are Pareto-optimal, and Graviton chips pack the efficiency frontier 3x denser than Intel.

  • Python
  • Pandas
  • Plotly
  • scikit-learn
318,604 price points 6.2% Pareto-optimal instance types

About

I'm a builder first — I'd rather ship the thing and learn from what breaks.

  • Now Software engineer intern at Ramedia Technologies, where I've shipped two production platforms end to end — real billing, real customers.
  • Studying MS Computer Science at Rutgers, finishing Dec 2026, after a BS in Computer Science and Applied Mathematics.
  • Building AI tools for problems I've actually seen — assistive tech for blind users, a rights platform for domestic workers, offline-first fitness.
2production platforms shipped at Ramedia
5+AI & full-stack projects, built top to bottom
2hackathon podiums — community impact award & 2nd overall
3.9GPA, MS Computer Science

Languages

  • Python
  • TypeScript
  • JavaScript
  • SQL
  • Java
  • C/C++

AI & ML

  • PyTorch
  • scikit-learn
  • LangChain
  • RAG
  • Gemini API
  • ONNX

Backend & Data

  • FastAPI
  • Node.js
  • Postgres
  • MongoDB
  • BigQuery
  • Snowflake

Frontend & Cloud

  • React
  • Next.js
  • React Native
  • Docker
  • AWS
  • Vercel

Experience

Where I've worked

  1. Jan 2026 — Jun 2026

    Software Engineer Intern · Ramedia Technologies

    Built and deployed two production web platforms (real-estate lead-gen and B2B industrial e-commerce). Integrated Stripe Checkout & webhooks, Google Maps, Firebase, and email APIs for $10K+/mo billing and live business workflows.

  2. Jan 2025 — Jun 2025

    ML & Cybersecurity Research Assistant · Rutgers University

    Built a Siamese Autoencoder intrusion-detection system on NSL-KDD (148K+ samples) in PyTorch with contrastive loss and curriculum learning, lifting accuracy from 54.7% to 82.1%. Authored two research papers.

  3. Jan 2025 — Apr 2025

    Teaching Assistant, Cybersecurity · Rutgers University

    Guided 25+ students on input validation, sanitization, and authentication in Python and TypeScript; ran Wireshark and Burp Suite lab sessions.

  4. Jan 2023 — Mar 2023

    Data Science Intern · LearnWik Solutions, Mumbai

    Worked with 1M+ rows of sales data in Python, applying regression and classification models; cut preprocessing time by 30% and delivered EDA reports for the marketing team.

Contact

Let's build something.

Open to software engineering, full-stack, and AI/ML roles. If something here resonated, I'd like to hear from you.

Say hello