kvjharsha

README.md



About Me
Hi, I'm K V Jaya Harsha a third-year undergraduate at IIIT Raichur with a strong interest in data engineering, MLOps, and scalable machine learning systems. I work at the intersection of cloud platforms, modern data pipelines, and AI workflows.
Currently, I’m focused on building production-grade ML pipelines using Azure and Databricks, applying best practices in modular design, monitoring, and orchestration. I’m also involved in full-stack web development and contribute to open-source projects at VISWAM AI.
My work spans from ingestion and transformation in cloud-based environments to deployment and observability in ML systems. I value clean design, automation, and reproducibility in every layer of the data and ML lifecycle.
Previously, I served as PR Head for student initiatives, where I led communications and outreach strategies.


Programming Languages
Data Engineering / Big Data
Databases
Data Science / ML / Analytics


Web Frameworks
Cloud / Hosting / DevOps
Containers / Orchestration
CI/CD / Version Control


Other Tools / Libraries


‎ 


🧠 Machine Learning Projects

  
      🌸 Iris Classifier

      A simple machine learning model trained on the classic Iris dataset to classify flower species based on sepal and petal measurements.


      🔧 Tech: Python, scikit-learn, Jupyter Notebook

      🔗 View Repository
    
    
      🌱 EcoCarb: Carbon Emission Prediction System

      🏆 Special Mention – National Hackathon

      EcoCarb is an AI-powered carbon footprint predictor for the transportation sector. It estimates CO₂ emissions from travel data, helping users and policymakers make eco-conscious decisions.


      🔧 Tech: Python, Machine Learning, Streamlit

      🔗 View Repository
    
  
🤖 RAG / Agent Projects

  
      ✈️ Flight Booking Agent

      An intelligent flight assistant powered by Groq's ultra-fast LLM acceleration and LLaMA 3 (8B). Built using LangGraph for modular agent flow and Gradio for an interactive UI. Handles itinerary queries, searches flights, and books tickets in natural language.


      🔧 Tech: Groq, LangGraph, LLaMA 3, Gradio

      🔗 View Repository
    
    
      💬 RAG-QnA Chatbot

      A Retrieval-Augmented Generation (RAG) based chatbot built using Streamlit, ChromaDB, and OpenAI API. Designed to ingest documents and answer user queries contextually with accurate, grounded responses.


      🔧 Tech: RAG, ChromaDB, Streamlit, OpenAI API

      🔗 View Repository
    
  
🏗️ Data Engineering Projects

  
      🌍 Azure Earthquake Data Pipeline

      A real-time data engineering pipeline built on Microsoft Azure. It ingests earthquake data via a public API, processes it using Azure Data Factory and Databricks (following the Medallion Architecture), and stores it in Synapse Analytics for dashboarding and alerting.


      🔧 Tech: Azure Data Factory, Databricks, Synapse Analytics, Python

      🔗 View Repository
    
  
💡 Feel free to explore, clone, or contribute to any of these projects!