Skip to content
View iamkunalkeshav's full-sized avatar
😀
😀
3 followers · 8 following
  • Accenture
  • Bengaluru

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Block or report iamkunalkeshav

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
iamkunalkeshav/README.md

Kunal Keshav

AI Engineer · Agentic Systems · RAG Pipelines

LinkedIn Portfolio Email

About

I'm an AI Engineer at Accenture (Bengaluru), building production-grade agentic AI systems and RAG pipelines for enterprise clients. Currently working on the Chubb insurance engagement — designing multi-agent workflows, retrieval pipelines, and LLM-powered APIs that run in production.

Pursuing M.Tech in CSE at PES University (2026–28) alongside full-time work.

  • 🤖 Building agentic systems with LangGraph and LangChain in production
  • 🔍 Designing and optimizing RAG pipelines for enterprise-scale document intelligence
  • 🛠️ Shipping FastAPI microservices consumed by real users
  • 🧑‍💻 Working daily with OpenAI and Anthropic APIs — certified in MCP (Model Context Protocol)
  • 📦 Indie-building Vanta — an AI mock interview trainer with adaptive follow-ups, real-time evaluation, and Hindi support

Tech Stack

Core AI/ML

LangChain LangGraph OpenAI Anthropic HuggingFace Pinecone

Languages & Backend

Python FastAPI TypeScript Next.js

Infrastructure & Data

Firebase PostgreSQL MongoDB Docker AWS

Featured Projects

🧠 Vanta — AI Mock Interview Trainer

Your personal AI interviewer that adapts in real-time

Full-stack web + desktop app built for serious interview prep. Conducts structured mock interviews, asks adaptive follow-up questions based on your answers, evaluates responses in real-time, and supports Hindi. Pro tier includes advanced analytics and role-specific question banks.

Stack: Next.js · FastAPI · Firebase · LLM APIs · Razorpay

🏢 Agentic RAG System — Chubb Insurance (Production)

Multi-agent document intelligence for enterprise insurance workflows

Designed and shipped a production agentic system with LangGraph-orchestrated agents, retrieval-augmented generation over proprietary insurance documents, and FastAPI-served endpoints integrated into client workflows.

Stack: LangGraph · LangChain · OpenAI · FastAPI · Vector DB

🔌 MCP-Powered Tooling

Certified in Anthropic's Model Context Protocol

Built and integrated MCP servers for agentic tool use — enabling LLMs to interact with external systems, APIs, and datastores in structured, composable workflows.

GitHub Stats

GitHub Streak Stats
Building AI systems that actually work in production · Bengaluru, India

Pinned Loading

  1. DSA DSA Public

    Python

  2. incident-summarizer-pro incident-summarizer-pro Public

    JavaScript

  3. rag-document-qa rag-document-qa Public

    Python

  4. secure-enterprise-rag secure-enterprise-rag Public

    A secure Enterprise RAG pipeline with multi-agent query routing (SQL, ChromaDB), strict Role-Based Access Control (RBAC), and grounded citations using LangChain and Groq.

    Python