Available for opportunities

Hi, I'm Devatva Rachit

~/ _

Final-year CS undergraduate at the intersection of backend engineering and applied AI — building scalable systems, RAG pipelines, and production-grade applications that turn data into insight.

01 02 03
scroll

Building at the intersection
of systems and intelligence.

A final-year Computer Science undergraduate driven by the intersection of backend engineering and applied AI. I focus on building scalable, data-driven systems — from Spring Boot-based backend platforms to machine learning and generative AI applications — that transform raw data into meaningful, real-time insights.

With a strong foundation in Java, system design, and ML workflows, I enjoy crafting practical, end-to-end solutions using modern frameworks and cloud-ready toolchains.

India CS Final Year Open to work Backend & AI
10+
Projects Built
20+
Technologies
15+
GitHub Repos
400+
Problems Solved

Technologies I work with

Languages
Frontend
Backend
Database
DevOps & Cloud
AI & ML

Things I've built

01
Featured npm
LLM Router MCP
MCP server that intelligently routes prompts across Gemini and Groq/Llama based on task intent — planning, codegen, testing, review — minimising token cost without sacrificing quality. Published as an npm package; integrates with Claude Desktop, Cursor, and VS Code.
TypeScript Node.js MCP SDK Gemini Groq npm
02
Featured Live ↗
Splitr — Expense Splitting App
Full-stack expense splitting app with guest mode, automatic cloud migration on sign-up, a minimum-payment settlement algorithm, and one-tap UPI deep-link payments. Row Level Security enforced at the Supabase database level.
React TypeScript Supabase PostgreSQL Tailwind CSS Vercel
03
Featured
Handwritten Equation Solver
Deep learning pipeline combining a CNN (96.97% character accuracy) with an RNN for sequence interpretation to recognise and solve handwritten mathematical equations from images. Served via a Streamlit web app with a live drawing canvas.
Python TensorFlow CNN RNN OpenCV Streamlit
04
Ledger — Personal Finance Dashboard
Personal finance dashboard tracking bills, recurring subscriptions with billing cycle normalisation, and tasks with priority levels. Includes an AI insights layer that flags unused subscriptions and upcoming payment risks.
React FastAPI Python MongoDB Tailwind CSS
05
YouTube RAG Chatbot
AI-powered chatbot that transforms any YouTube video into an interactive Q&A experience using LangChain and Retrieval-Augmented Generation, achieving 25–35% improvement in answer relevance over baseline LLM responses.
Python LangChain RAG Vector Embeddings LLM NLP

Let's build something
together.

I'm currently open to new opportunities. Whether you have a project in mind, a role to discuss, or just want to connect — drop me a message.

India, IST
--:--:--