Skip to content
View MuhammadSamarShehzad's full-sized avatar

Block or report MuhammadSamarShehzad

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

Hi, I'm Muhammad Samar Shehzad πŸ‘‹

AI Developer & Machine Learning Engineer
Building Production LLM Applications β€’ Agentic AI β€’ RAG Systems

🌐 Portfolio β€’ πŸ’Ό LinkedIn β€’ πŸ“§ Email


πŸš€ About Me

AI Developer specializing in LLM applications, Agentic AI systems, and RAG architectures.
Currently building production-ready AI solutions at InterCraft, focusing on intelligent automation and real-time AI agents.

  • πŸ”₯ Currently Working On: Agentic RAG systems, Real-time AI agents with LiveKit, Local LLM deployment
  • 🌱 Learning: AWS AI Services (SageMaker, Bedrock), Cloud deployment
  • πŸŽ“ BSCS (CGPA 3.87) β€” Arid Agriculture University Rawalpindi
  • πŸ’‘ Passionate About: Building scalable AI systems that solve real-world problems

πŸ› οΈ Tech Stack

Languages & Frameworks
Python SQL FastAPI Streamlit

AI/ML & LLM Tools
LangChain LangGraph scikit-learn Keras NumPy Pandas

Cloud & DevOps
AWS Docker Git

Core Skills
RAG Systems β€’ Agentic AI β€’ Prompt Engineering β€’ NLP β€’ Computer Vision β€’ Real-time AI (LiveKit) β€’ Local LLM Deployment


πŸ† Featured Projects

Autonomous coding agent automating code modifications and analysis using Google ADK and LangGraph.
Tech: RAG-based retrieval, multi-agent orchestration, automated testing, semantic embeddings

Vision-enabled AI agent with real-time video interactions, TTS/STT capabilities using LiveKit.
Tech: LiveKit, Computer Vision, Conversational AI

Intelligent assistant for semantic search across Quran, Hadith, and Fatwa sources.
Tech: Google ADK, LangChain, HuggingFace, FastAPI, Streamlit, Docker

CNN-based medical image classification achieving 99.15% accuracy using DenseNet201.
Tech: TensorFlow, Keras, Deep Learning, Computer Vision

Predictive model with 97% accuracy for early diabetes detection.
Tech: Scikit-learn, Data Preprocessing, Classification Algorithms


πŸ“Š GitHub Stats

GitHub Stats Top Languages


🎯 Current Focus

  • Building Agentic RAG architectures for autonomous AI systems
  • Deploying production AI solutions on AWS (EC2, S3, Lambda, SageMaker)
  • Exploring multi-agent collaboration and context engineering
  • Contributing to open-source AI/ML projects

"Building intelligent systems that create measurable impact."

⭐️ From MuhammadSamarShehzad

Pinned Loading

  1. Diabetes-Prediction Diabetes-Prediction Public

    Diabetes Prediction using Machine Learning

    Jupyter Notebook

  2. Email_Classification Email_Classification Public

    Spam Email Classification

    HTML

  3. Heart-Disease-Prediction Heart-Disease-Prediction Public

    Heart Disease Prediction using Machine Learning

    Jupyter Notebook

  4. Skin-Cancer-Classification Skin-Cancer-Classification Public

    Skin Cancer Classification using Transfer Learning

    Jupyter Notebook

  5. PalestineIsrael-InjuriesAndDeaths PalestineIsrael-InjuriesAndDeaths Public

    Palestine-Israel Conflict Dashboard

    Jupyter Notebook