Skip to content
View Dhananjay-prod's full-sized avatar
💭
building
💭
building
0 followers · 8 following

Block or report Dhananjay-prod

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
Dhananjay-prod/README.md 
██████╗ ██╗  ██╗ █████╗ ███╗   ██╗ █████╗ ███╗   ██╗     ██╗ █████╗ ██╗   ██╗
██╔══██╗██║  ██║██╔══██╗████╗  ██║██╔══██╗████╗  ██║     ██║██╔══██╗╚██╗ ██╔╝
██║  ██║███████║███████║██╔██╗ ██║███████║██╔██╗ ██║     ██║███████║ ╚████╔╝ 
██║  ██║██╔══██║██╔══██║██║╚██╗██║██╔══██║██║╚██╗██║██   ██║██╔══██║  ╚██╔╝  
██████╔╝██║  ██║██║  ██║██║ ╚████║██║  ██║██║ ╚████║╚█████╔╝██║  ██║   ██║   
╚═════╝ ╚═╝  ╚═╝╚═╝  ╚═╝╚═╝  ╚═══╝╚═╝  ╚═╝╚═╝  ╚═══╝ ╚════╝ ╚═╝  ╚═╝   ╚═╝

AI & ML Engineer · LLM Systems · Agentic AI

Building systems that think, reason, and act — not just predict.

LinkedIn Email LeetCode Kaggle

whoami

dhananjay = {
    "role"        : "AI & ML Engineer (2024 BE Graduate)",
    "focus"       : ["LLM Systems", "Agentic AI", "RAG Pipelines"],
    "currently"   : "Learning AWS + Cloud Deployments",
    "roadmap"     : "Docker → AWS → MLOps → CI/CD → Kubernetes",
    "open_to"     : "AI/ML Engineering roles across India (remote-friendly)",
    "fun_fact"    : "I can make you laugh :)"
}

🚀 Featured Projects

🤖 Langie — Autonomous Translation Agent

11-stage LangGraph StateGraph agent with dual-server MCP architecture and 25+ dynamic state variables. Powered by Gemini 2.0 Flash.

LangGraph MCP Gemini 2.0 Multi-Agent Python

🧠 Predixa — Multi-Task Sentiment Engine

DistilBERT with dual CrossEntropy/MSE loss heads trained on ~763K Amazon reviews. Deployed as a Flask REST API.

PyTorch HuggingFace DistilBERT Flask Multi-Task Learning

🔍 RAG Pipeline — Production-Grade Retrieval System

End-to-end pipeline with LangChain, Pinecone vector store, GTE-Large embeddings, Cohere reranking, and Chainlit streaming interface.

LangChain Pinecone Cohere Chainlit GTE-Large

⚡ TaviGemChain — Real-Time Web RAG

Live web search RAG combining Tavily search API with Gemini 2.0 Flash for grounded, real-time responses.

Tavily Gemini 2.0 LangChain Real-Time RAG

🛠️ Tech Stack

LLM & AI

Python PyTorch HuggingFace LangChain Pinecone

Backend & APIs

FastAPI Flask PostgreSQL MongoDB

Cloud & DevOps — Currently Learning ⚡

AWS Docker GitHub Actions

📡 Current Learning Roadmap

2025 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2026

[✅ Done]     Python · PyTorch · LangChain · LangGraph · RAG · FastAPI
[🔄 Now]      Docker · AWS Core Services (EC2, S3, Lambda, ECR)
[⏭ Next]      MLflow · DVC · GitHub Actions CI/CD
[🔜 Soon]     Kubernetes · Terraform · Monitoring & Observability

Goal: Deploy Predixa and Langie as live public APIs with full CI/CD pipelines.

📊 GitHub Stats

Dhananjay's GitHub Stats

Top Languages

"The best way to understand a system is to find where it breaks."

📬 dhananjaykumar137c@gmail.com · Open to AI/ML roles across India

Pinned Loading

  1. Chatpdf Chatpdf Public

    An AI-powered chatbot that extracts knowledge from PDFs using LangChain, stores embeddings in Pinecone, and answers questions with Falcon-7B LLM and Cohere reranking for accurate, context-aware res…

    Python

  2. PDF-Question-Answering-App-using-RAG-and-Chainlit PDF-Question-Answering-App-using-RAG-and-Chainlit Public

    A seamless PDF Question Answering application using Retrieval-Augmented Generation (RAG) with an interactive Chainlit frontend. Upload a PDF, get it processed and chunked, generate vector embedding…

    Python 1