Skip to main content
Rohit Raj
StartseiteProjekteServicesReposNotizenÜber michKontaktAktuelle Arbeit

Ein Founding Engineer aus Indien, der End-to-End auf jedem Stack liefert — KI, Backend, Mobile, Blockchain, iOS, Web3 — ohne die Kosten eines Teams.

Bringen Sie Ihr KI-MVP in 6 Wochen live.
29 Produkte ausgeliefert, jedes dokumentiert.

6-Wochen-MVP-Sprint · 50 % zurück, wenn wir den Woche-3-Meilenstein verfehlen
Kostenloses 30-Min-Gespräch buchenKI ProjekteEngineering Notes
  • Festpreis · Keine Stundenüberraschungen
  • Sie besitzen den Code · MIT oder kommerziell
  • Täglicher Slack-/WhatsApp-Zugriff
  • Erster Produktions-Commit in 5 Tagen
AI and Backend Systems Architecture
KI Projekte

Produktionsreife KI-Systeme

Keine Experimente — Full-Stack Anwendungen mit echter Infrastruktur.

01

MicroItinerary — AI Travel Planner

liveSource

Problem

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

Lösung

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

KI-Ansatz

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

Build time
6 weeks
GPT-4 cost / itinerary
<$0.08
PWA Lighthouse
94/100
React 18ViteSpring Boot 3.2.2Java 21PostgreSQL 16RedisOpenAI GPT-4
02

StellarMIND — Chat-to-SQL with pgvector

liveSource
StellarMIND — Chat-to-SQL with pgvector

Problem

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

Lösung

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

KI-Ansatz

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

Query latency p95
<1.2s
SQL safety
100% read-only
Schema embeddings
pgvector
Spring BootSpring AIPostgreSQLpgvectorMCP ProtocolOpenAI
03

MyFinancial — Personal Financial Advisor

liveLiveSource
MyFinancial — Personal Financial Advisor

Problem

Financial planning in India is fragmented across banks, insurance, and tax documents. Most tools require sharing sensitive data with third parties.

Lösung

Privacy-first PWA that consolidates financial data locally via a 6-step wizard — Profile, Income, Assets, Liabilities, Insurance, Tax — with real-time advisory metrics like Financial Runway and Savings Rate.

KI-Ansatz

Rule-based advisory engine for Indian financial instruments (PPF, EPF, NPS). Old vs. New Tax regime comparison. Coverage gap analysis for insurance. No cloud dependency — all computation runs locally.

Data privacy
100% on-device
Wizard completion
6 steps · ~4 min
Tax regimes covered
Old + New
React 19Vite 7Tailwind CSS 4ZustandDexie (IndexedDB)Spring Boot 3.xJava 21PostgreSQL
Engineering Notizen Lesen → →
Process

How a 6-week MVP sprint works

Fixed scope. Daily Slack. First production commit by day 5.

  1. 01
    Week 1

    Discovery & architecture

    • Problem framing call
    • Architecture doc
    • Tech stack lock-in
  2. 02
    Week 2

    Core backend & auth

    • Database schema
    • Auth flow
    • First production deploy on day 5
  3. 03
    Week 3

    AI / data layer

    • LLM integration
    • Vector store + retrieval
    • Cost guardrails
  4. 04
    Week 4

    Frontend & UX

    • UI flows
    • Mobile responsive
    • Analytics events
  5. 05
    Week 5

    Hardening

    • Load tests
    • Observability
    • Security pass
  6. 06
    Week 6

    Launch

    • Bug bash
    • Public deploy
    • Code handover + docs
Engineering Qualität

Zuverlässigkeit & Produktionsreife

📊

Observability

Prometheus + Grafana

Produktionsreife Metriken, Dashboards und SLO-Sichtbarkeit.

  • RED/USE Metriken mit benutzerdefinierten Business-KPIs
  • Grafana Dashboards für Latenz, Durchsatz, Fehlerraten
  • Alerting und umgebungsspezifische Scrape-Konfiguration
Mehr erfahren →
⚡

Lasttests

k6

Performance-Validierung für event-driven Systeme mit hohem Durchsatz.

  • Szenariobasierte Tests (Ramping, Soak, Constant-Arrival-Rate)
  • Schwellenwerte für p95/p99 Latenz und Fehlerraten
  • CI-kompatible Ausführung und Berichte
Mehr erfahren →
🔗

API Contract Testing

Postman + Newman

Wiederholbare Regressions- und Smoke-Tests für REST APIs.

  • Umgebungsgesteuerte Collection-Ausführung
  • Newman CLI mit HTML/JUnit Reports
  • Pipeline-freundliche Contract-Validierung
Mehr erfahren →
📨

Event-Driven Testing

Kafka Simulation

Deterministische Tests von Kafka Consumern und Workflows.

  • Geforkte Kafka-Simulations-Repos für Event-Replay
  • Partitionierungs- und Reihenfolge-Validierung
  • Failure-, Retry- und Backpressure-Tests
Mehr erfahren →
Testimonials

What Clients Say

Rohit delivered our MVP in 5 weeks — on budget and ahead of schedule. His architecture decisions saved us from rewriting everything when we scaled.

Arjun Kapoor
Founder, NovaByte Labs
MVP Development

We needed a WhatsApp bot for our clinic chain. Rohit understood the problem immediately and shipped a working solution that our staff could use without training.

Priya Mehta
CTO, MediConnect Health
WhatsApp Bot

What impressed me most was the transparency. GitHub access from day one, weekly demos, no surprises. The React Native app he built is still running with zero issues.

Vikram Desai
Product Manager, FinLeap Technologies
Mobile App
FAQ

Common questions before we start

What if 6 weeks slips?

Fixed scope means we descope features, not extend timeline.

Who owns the code?

You. Full repo handover on week 6.

Am I locked into your tech stack?

No. I'll ship in your stack if your team has one.

Refund policy?

50% back if we miss the week-3 production deploy milestone.

Rohit Raj — Backend & KI-Systeme Ingenieur

Services

Mobile App DevelopmentAI Chatbot DevelopmentFull-Stack Development

Updates Erhalten