Not tutorial apps. Not sandboxes. Real systems — running right now, serving real people.
- 🚆 Railway Vendor System — cut login from 30–60s → under 5s, data fetch from 2 min → 10s. Joined as bug fixer; consistently resolved issues faster than the existing team — manager handed full ownership across 4 Indian Railways divisions.
- 🍽️ QR-Based Train Pantry Ordering System — unique QR per train, live vendor menu updated in real-time, 3-role system (User · Vendor · Admin); co-built with teammate.
- 🗺️ GeoTech Garbage & Material Management System — GPS-tagged photo reporting, full 6-role lifecycle: report → assign → clean → verify → approve → notify; co-built with teammate.
- 🎓 ID Card & Face Verification System — multi-role workflow with QR codes and face detection, used by 10,000+ students and staff at 20+ institutes. Built entire backend solo.
- 🏛️ Government of India Copyright holder — Reg. L-151429/2024 for an AI image forgery detection system built with CNN + ELA.
- 📄 3 published research papers in Computer Vision and NLP.
I move fast, write clean code, and take full ownership of what I build.
| 10,000+ | 12× | 8 Live | 4 | 3 | 1 |
|---|---|---|---|---|---|
| Users on systems I built | Performance gain on railway backend | Production apps delivered | Railway divisions deployed | Published research papers | Govt. of India copyright |
Dec 2025 – Present
Railway Vendor Management System — 4 Indian Railways Divisions, Maharashtra & Chhattisgarh
- Joined as bug fixer; resolved critical issues faster than senior developers — manager handed full project ownership
- Now sole maintainer across all 4 divisions with daily commits to private repository
- Optimized login 30–60s → under 5s, data fetch 2 min → under 10s (12× improvement each)
QR-Based Train Pantry Ordering System
- Co-built (50-50) with 1 teammate via Git + Google Meet
- Designed full UI; each train has a unique QR opening a live vendor menu with real-time updates
- 3-role system: User orders → Vendor receives and delivers → Admin monitors sales, ratings, complaints
GeoTech Garbage & Material Management System
- Co-built (50-50) with 1 teammate via Git + Google Meet
- GPS-tagged photo reporting with auto-captured coordinates; full 6-role lifecycle: report → assign → clean → verify → approve → notify
- Includes Material Storage module for railway scrap inventory with live weight tracking
Institute ID Card & QR Verification System — 20+ Institutes, 10,000+ Users
- 2-person team via Git + Google Meet; solely built entire backend
- Multi-role workflow: Admin → Org Admin → Employee/Student with face detection and QR-based verification
- Maintained direct client communication throughout delivery
Multi-tenant SaaS bug tracking with AI-powered triage — production-grade from the ground up.
- RBAC with Admin, Developer, and Tester roles — scoped data access at every layer
- AI triage — auto-assigns severity, deduplicates issues, generates reproduction steps via OpenAI
- Auth — JWT + BCrypt + Spring Security, containerized with Docker
- Architecture — Controller–Service–Repository + DTO, @Transactional on service layer
Java 17·Spring Boot 3·Spring Security 7·MySQL 8·React·Redux·OpenAI API·Docker
Real static analysis — not just LLM opinions.
- AST parsing via
acorn— structural analysis, not surface-level feedback - Cyclomatic complexity scoring + maintainability metrics across 10 languages
- GitHub URL mode — paste any public file URL and review it directly
- Chose Groq over OpenAI — 14,400 free req/day, same SDK, zero cost; stateless backend
Node.js·Express·React 18·Vite·Groq API (llama-3.3-70b)·acorn AST
AI system for detecting image manipulation — backed by a government copyright and 3 research papers.
- CNN + ELA (Error Level Analysis) to detect JPEG artifact manipulation with high accuracy
- REST API with heatmap overlay showing exactly where tampering occurred
- Foundation for 3 published papers in AI/ML conferences
Python·TensorFlow·OpenCV·Flask·CNN·ELA
| # | Title | Domain |
|---|---|---|
| 1 | AI-Based Image Forgery Detection using CNN + ELA — Govt. Copyright Registered | Computer Vision · Security |
| 2 | AI Image Enhancement using Deep Learning | Computer Vision |
| 3 | AI Mock Interview & NLP-based Feedback Analysis | NLP · EdTech |
I'm looking for SDE-1 / Backend / Full Stack roles. Immediate joiner — open to relocation and remote.
If you need someone who ships real software and takes ownership, I'd love to connect.