Skip to content
View ChetanVK10's full-sized avatar

Block or report ChetanVK10

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
ChetanVK10/README.md

Hi there, I'm Chetan Viswa Kumar 👋

GenAI / LLM Engineer  |  Building Production-Oriented Agentic AI Systems

LinkedIn Email


🚀 About Me

  • 🧠 AI / GenAI Engineer focused on Agentic AI, LLM applications, RAG, and LLM evaluation
  • ⚙️ Built and engineered 3 end-to-end GenAI systems spanning agentic research, autonomous data analysis, and LLM evaluation/observability
  • 🔧 Experienced with LangGraph, FastAPI, Qdrant, DuckDB, PostgreSQL, MCP, and multi-provider LLM architectures
  • 📄 Co-author of 3 IEEE conference publications covering Explainable AI and healthcare machine learning
  • 🎯 Interested in GenAI Engineer · LLM Engineer · Agentic AI Engineer roles

🧰 Tech Stack

AI / LLM Engineering Backend & Data
               
Machine Learning Languages & Tools
               

🔍 Multi-Source Research Agent Agentic RAG assistant built with LangGraph + FastAPI + Qdrant, delivering citation-backed answers by combining document and web-based retrieval (Tavily Search).

LangGraph FastAPI Qdrant Tavily

🗃️ DataAgent-Pro Stateful multi-agent data analysis system (Planner → SQL Generator → Executor → Validator → Reflection) with a live agent-trace UI for transparent, auditable Text-to-SQL reasoning.

LangGraph DuckDB PostgreSQL React MCP

📊 LLMOps-Studio Full-stack LLM evaluation platform for experiment tracking, multi-provider benchmarking, regression detection, and automated promotion gates.

FastAPI PostgreSQL Docker React

🏥 Health Insurance Fraud Detection ML system to flag fraudulent health insurance claims using XGBoost & SVM with SMOTE-based class balancing and engineered features. Basis for two IEEE publications.

XGBoost SVM SMOTE

💳 Loan Application Website — React-based loan application platform with role-based dashboards for users and admins, and live form validation.


📄 Publications

  • QR Code Based AR Navigation for Hospitals — ICAMIDA 2025
  • An Explainable Artificial Intelligence Approach to Health Insurance Claim Fraud Detection — ICAIIHI 2025
  • A Hybrid Machine Learning Approach for Fraud Prevention and Health Insurance Claim Verification — IATMSI 2026

Building AI that doesn't just generate — it retrieves, reasons, executes, and verifies.

Let's build something meaningful.

Pinned Loading

  1. LLMOps-Studio LLMOps-Studio Public

    Full-stack LLM evaluation platform for experiment tracking, multi-provider evaluation, regression detection, and automated promotion gates.

    TypeScript

  2. DataAgent-Pro DataAgent-Pro Public

    Stateful multi-agent AI data analysis system built with LangGraph, FastAPI, DuckDB, PostgreSQL, React, and MCP.

    Python

  3. Multi-Source-Research-Agent Multi-Source-Research-Agent Public

    Agentic AI research assistant built with LangGraph, FastAPI, Qdrant, and Tavily Search for grounded document and web-based question answering with citations.

    Python

  4. Health-Insurance-Fraud-Claim-Detection Health-Insurance-Fraud-Claim-Detection Public

    An intelligent machine learning system to detect fraudulent health insurance claims using XGBoost and SVM with data balancing (SMOTE) and advanced feature engineering.

    Jupyter Notebook

  5. Loan-Project Loan-Project Public

    Loan Application Website — React frontend for a secure, user-friendly loan application system. Features role-based dashboards for users and admins, live form validations, and seamless integration w…

    JavaScript