8000 pratikjadhav2726 (Pratik Shankar Jadhav) · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View pratikjadhav2726's full-sized avatar

Highlights

  • Pro

Block or report pratikjadhav2726

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
pratikjadhav2726/README.md

Hey there 👋, I'm Pratik Shankar Jadhav

I'm an AI/ML Engineer who loves building practical AI systems — the kind that don't just sit on papers, but actually work in production.

By day, I’m architecting scalable LLM + RAG + Agentic AI pipelines for enterprise use cases at UNIS (3PL / Logistics AI).
By night (and sometimes weekends), I’m tinkering with GraphRAG, Neo4j-powered tool graphs, multimodal AI, and the occasional diffusion model.

Oh, and I’m also passionate about 🧮 math, 🐈 cats, and 🤖 agentic AI.


🛠️ What I Do

  • LLM Engineering: Fine-tuning, PEFT (LoRA, QLoRA), quantization, model distillation
  • RAG Architectures: Self-RAG, GraphRAG, RAPTOR-based retrieval, Neo4j + VectorDBs
  • Agentic AI: MCP server orchestration, LangGraph-based tool agents, dynamic tool retrieval
  • MLOps & Deployment: MLflow, Docker, Kubernetes, AWS SageMaker & Bedrock
  • Data Science: NLP, CV, RLHF, Speech Processing, Recommender Systems

🔍 Projects I’m Proud Of


👨🏻‍💻 Past Lives

  • AI System Specialist - UNIS (2025-Present)
    Building AI-driven solutions for logistics & supply chain optimization.

  • Research Engineer & TA - CSULB (2023-2025)
    Optimizing LLMs and teaching GenAI. Also wrote a thesis on Diffusion-based TTS.

  • AI/ML Software Engineer - Cognizant (2021-2022)
    Developed pilot scheduling optimization systems for Alaska Airlines.


✨ Fun Facts

  • I’m an AI engineer who still loves pure math — topology and number theory fascinate me.
  • I’ve trained agents to pick tools smarter than some humans (I kid… or do I?).
  • I believe Agentic AI will change how we build software — one tool call at a time.
  • I have an unreasonable number of cat memes in my downloads folder.

📫 Let’s Connect


“The best AI systems feel like magic but work like math.” — probably me, during a late-night coding session.

Pinned Loading

  1. Unified-MCP-Tool-Graph Unified-MCP-Tool-Graph Public

    Instead of dumping 1000+ tools into a model’s prompt and expecting it to choose wisely, the Unified MCP Tool Graph equips your LLM with structure, clarity, and relevance. It fixes tool confusion, p…

    Python 8 1

  2. csulb-datascience/TTS-with-Diffusion-model csulb-datascience/TTS-with-Diffusion-model Public

    Jupyter Notebook 1 1

  3. MedGPT MedGPT Public

    MedGPT: Multimodal Large Language Model for Medical Insights:- MedGPT is an advanced multimodal system combining the power of Large Language and Vision Models (LLMs) to interpret medical images and…

    Jupyter Notebook 4

  4. Generative-UI-chat Generative-UI-chat Public

    This project is a Next.js-based chatbot that leverages Large Language Models (LLMs) to generate dynamic UI templates based on user requests. The assistant can respond with structured UI configurati…

    TypeScript 1

  5. Research Research Public

    Welcome to the Research & Prototype Repository by @pratikjadhav2726 — a curated and expanding archive of experimental ideas, novel ML techniques, and practical research codebases designed for open …

    Jupyter Notebook

  6. Sales_Agent_Langgraph Sales_Agent_Langgraph Public

    An enterprise-grade AI sales assistant for SolarSmart products, offering personalized interactions with Retrieval-Augmented Generation (RAG) for swift information access. It uses session-based memo…

    Python 1

0