Rohit Raj — Backend & AI Engineer

Building AI Systems
That Solve Real Problems

My Approach

  • Problem First — Identify the real user pain before writing code
  • AI as a Tool — Use LLMs where they add value, not as a gimmick
  • Production-Ready — Every project includes infra, testing, and deployment
  • Open Engineering — Document decisions, trade-offs, and failures publicly
View AI ProjectsEngineering NotesGitHub
AI and Backend Systems Architecture

AI Projects

Production-Ready AI Systems

Not experiments — full-stack applications with real infrastructure.

MicroItinerary — AI Travel Planner

development

Problem

Travel apps optimize for proximity and ratings. They don't consider human energy levels, group dynamics, or budget constraints intelligently.

Solution

AI-powered PWA that generates personalized annual travel itineraries with intelligent destination suggestions, cost estimation in INR, and Splitwise-style expense splitting.

AI Approach

GPT-4 for destination recommendations based on season, budget, and preferences. AI-generated cost breakdowns for hotels, food, transport, and activities.

Tech Stack

React 18ViteSpring Boot 3.2.2Java 21PostgreSQL 16RedisOpenAI GPT-4

StellarMIND — Chat-to-SQL with pgvector

development

Problem

Business users need to query databases without knowing SQL. Existing tools lack context-aware query generation and safety guarantees.

Solution

Spring Boot MCP server that converts natural language questions into read-only SQL using LLM with retrieval-augmented context from pgvector.

AI Approach

RAG-based SQL generation: schema knowledge stored as embeddings in pgvector, retrieved as context for LLM. Strict read-only enforcement (only SELECT/WITH).

Tech Stack

Spring BootSpring AIPostgreSQLpgvectorMCP ProtocolOpenAI
Read full architecture notes →