Skip to content
View Jayasoruban's full-sized avatar

Block or report Jayasoruban

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jayasoruban/README.md
header

 Ex-Walmart   ·   Ex-Caterpillar   ·   Chennai, India 🇮🇳 



tagline



       



✨   At a Glance

Who I am

Software engineer with 4+ years at Fortune 500 companies — Walmart and Caterpillar — now focused full-time on AI engineering.

I build LLM-powered products end-to-end — from agent orchestration and RAG pipelines on the backend to polished React UIs on the frontend.

No hype. No vaporware. Production-ready AI systems that solve real business problems.

Right now

  • 🚀 Shipping 6 production AI projects in 30 days
  • 📚 Deep-diving LangGraph, CrewAI, and MCP
  • 🧠 Exploring multi-agent evaluation and observability
  • 💼 Accepting new freelance engagements (Q4 2026)
  • 📍 Based in Chennai, India · remote-first
  • Response time: within 24 hours

💼   Experience

Walmart
Walmart

Software Engineer III

Backend engineering on large-scale distributed systems for one of the world's largest retailers. Python, Java, microservices, cloud infrastructure, high-throughput data pipelines.

Caterpillar
Caterpillar Inc.

Software Engineer

Built real-time asset tracking and logistics services using Java, Spring Boot, REST APIs, and AWS. Shipped the proof-of-concept that became a global logistics platform.


🧠   What I Build

🤖 AI Agents & Multi-Agent Systems

Orchestrated agent workflows using LangGraph, CrewAI, and MCP — with evals, tracing, and human-in-the-loop controls.

Typical engagement: $15K – $50K · 3–6 weeks

📚 RAG Systems

Retrieval-augmented chat over private document corpora using ChromaDB, Pinecone, hybrid search, and cited answers.

Typical engagement: $5K – $15K · 2–4 weeks

⚡ LLM Workflow Automation

Business-system integrations with n8n, custom Python pipelines, and API orchestration across CRMs, databases, Slack, and more.

Typical engagement: $2K – $8K · 1–2 weeks

🌐 Full-Stack AI Products

End-to-end MVPs: Next.js UI + FastAPI backend + LLM + auth + payments + deployment. Design → ship.

Typical engagement: $10K – $30K · 4–8 weeks


🛠️   Tech Stack

AI · LLM · Agents

LangChain LangGraph CrewAI MCP OpenAI Claude LangSmith HuggingFace

Backend

Python FastAPI Node.js PostgreSQL Redis Docker

Frontend

Next.js React TypeScript Tailwind Vercel

Vector Stores · Data

ChromaDB Pinecone Weaviate Qdrant

Infra · DevOps

AWS Railway n8n Git


🚀   Featured Projects   (shipping now — 6 in 30 days)

🔍 DocuMind

RAG Chatbot over Custom Docs

LangChain · ChromaDB · Streamlit

Upload PDFs → chat with them → get cited answers.

🚧 In Progress — Week 1

🧑‍🔬 ResearchCrew

Autonomous Multi-Agent Researcher

CrewAI · Tavily · Next.js

3 agents collaborate to produce full market research reports.

📋 Planned — Week 2

⚡ LeadQualifier

AI Workflow Automation

n8n · OpenAI · HubSpot

Auto-score leads → enrich → route. Self-hosted.

📋 Planned — Week 3

🗄️ DB-MCP

Natural Language DB Assistant

MCP · PostgreSQL · Claude

Query your database in plain English via Claude Desktop.

📋 Planned — Week 3

✨ ContentForge

Full-Stack AI SaaS MVP

Next.js · FastAPI · Stripe

AI blog post generator with SEO. End-to-end product.

📋 Planned — Week 4

🎙️ VoiceBook

AI Voice Appointment Agent

LiveKit · Deepgram · ElevenLabs

Real-time voice AI that books appointments over the phone.

📋 Planned — Month 2


📊   GitHub Stats


🤝   Let's Build Something

I take on 4–5 clients at a time so every project gets real attention. If you're building something AI-powered and need an engineer who ships, I'd love to hear about it.




Built with Python, caffeine, and a lot of LLM calls.

Pinned Loading

  1. documind-rag-chatbot documind-rag-chatbot Public

    📚 DocuMind — Production-grade RAG chatbot. Chat with your PDFs, get cited answers. LangChain · OpenAI · ChromaDB · Streamlit.

    Python 1

  2. anything-llm-rebuild anything-llm-rebuild Public

    A from-scratch rebuild of AnythingLLM to learn production-grade LLM systems. Phase-by-phase build log in commit history.

    JavaScript