Skip to content
View mrutunjay-kinagi's full-sized avatar
:octocat:
Hello !
:octocat:
Hello !
12 followers · 48 following

Achievements

Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report mrutunjay-kinagi

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 supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mrutunjay-kinagi/README.md

👋 I'm Mrutunjay Kinagi

Senior AI Product Engineer & Distributed Systems Engineer Hardening the Agentic AI ecosystem and building the infrastructure that powers LLMs at scale.

I am a Builder-Owner with 9+ years of experience specializing in the "Last Mile" of AI—taking complex agentic concepts and turning them into stable, production-grade systems.

🛠️ Open Source & Contributions

I believe in hardening the tools I use. My recent work focuses on stability, orchestration, and data integrity.

  • LlamaIndex: Improved tool_choice and parallel execution logic for reliable agentic loops.
  • Apache Camel: Resolved core recursion and stack overflow issues (CAMEL-23030) in high-concurrency executors.
  • Apache Iceberg: Enhanced REST catalog capabilities and validated snapshot integrity for distributed data lakes.
  • Model Context Protocol (MCP): Active contributor to the Python SDK, focusing on OAuth stability and context forwarding.

🚀 Technical Arsenal

  • Agentic AI: Multi-model orchestration (LangGraph, LlamaIndex), Model Context Protocol (MCP), RAG, and Context Engineering.
  • Distributed Systems: Microservices, High-concurrency architectures, Cloud-Native development (AWS).
  • Modern Workflow: AI-native development leveraging Cursor and Claude Code for extreme shipping velocity.
  • Languages: Python, TypeScript, Rust, Java, Node.js.

🌟 Achievements & Certifications

  • Open Source Advocate: Regular contributor to mission-critical infrastructure projects (Apache, LlamaIndex, LangChain).
  • OCAJP: Oracle Certified Associate Java Programmer.
  • M.Sc. in Computer Science: Scaler Neovarsity (Woolf, Europe).

📫 Let's Collaborate

"I don't just build with AI; I build the tools that make AI work in the real world."

Pinned Loading

  1. mrutunjay-kinagi mrutunjay-kinagi Public

  2. ragsearch ragsearch Public

    This project aims to build a Retrieval-Augmented Generation (RAG) engine to provide context-aware recommendations based on user queries.

    Python 3 2

  3. no-cap-stock-feed no-cap-stock-feed Public

    A data pipeline to process real-time stock market data using Kafka, Spark, and Apache Iceberg with dbt for transformations and Prefect for orchestration.

    Python 2

  4. api-aesthetic api-aesthetic Public

    A curated collection of API protocols (AMQP, MQTT, gRPC, REST, and more), showcasing real-world use cases with a sleek Streamlit interface. A backend-heavy exploration of modern and legacy API comm…

    Python 2 1

  5. Daft Daft Public

    Forked from Eventual-Inc/Daft

    Distributed DataFrame for Python designed for the cloud, powered by Rust

    Rust

  6. iceberg iceberg Public

    Forked from developer-advocacy-dremio/iceberg-intro-lessons

    POC using Iceberg