Skip to content
View sanjaykunta's full-sized avatar

Block or report sanjaykunta

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
sanjaykunta/README.md

Hi, I'm Sanjay Kunta

Senior Software Engineer transitioning into AI Engineering, with full-stack fintech experience and hands-on projects in Agentic AI, RAG, LangGraph, MCP, FastAPI, Java, Python, and cloud-native backend systems.

Focus Areas

  • Agentic AI systems with LangGraph and CrewAI
  • Retrieval-Augmented Generation with citations and verification
  • MCP-based tool integrations for AI agents
  • Backend APIs using FastAPI, Java, and Spring Boot
  • Testable, production-style engineering with CI, Docker, and clean architecture

Featured Projects

Multi-Agent Coding Assistant

LangGraph-based coding assistant that converts software requirements into design, implementation code, tests, and code review using RAG, MCP, FastAPI, and Gemini/Vertex AI.

Tech: Python, LangGraph, FastAPI, MCP, Gemini, RAG, Docker, pytest

DocuVerify RAG

Agentic RAG system that answers questions over documents using hybrid BM25/vector retrieval, source citations, verification, and self-correction.

Tech: Python, CrewAI, LangChain, BM25, OpenAI embeddings, Gemini, Gradio, pytest

Currently Building

  • Production-style AI engineering portfolio projects
  • Agentic AI systems with tool use and verification loops
  • Java + AI backend services for enterprise use cases

Connect

  • LinkedIn: add your LinkedIn URL
  • GitHub: github.com/sanjaykunta

Pinned Loading

  1. multi-agent-coding-assistant multi-agent-coding-assistant Public

    Multi-agent coding assistant using LangGraph, Vertex AI Gemini, embedding-based RAG, and MCP client/server tooling to generate implementation code, tests, and code reviews from software requirements.

    Python

  2. docuverify-rag docuverify-rag Public

    Built a Python agentic RAG pipeline with hybrid BM25/vector retrieval, source citations, verification, and self-correction to reduce unsupported AI answers.

    Python