🧠 Machine Learning & AI Practice Lab

Welcome to my personal engineering sandbox. This repository serves as a comprehensive log of my journey through advanced Artificial Intelligence, Machine Learning architectures, and System Design patterns.

As a C/C++ Systems Programmer and AI/ML Practitioner, I approach these topics with a focus on performance, scalability, and low-level understanding.

📚 Repository Structure

This repository is organized into three main pillars, reflecting my current engineering focus:

1. 🤖 Agentic AI & LLMs

Explorations into autonomous agents, orchestration, and cognitive architectures.

• Focus Areas: Multi-agent workflows, tool use, memory management, and RAG (Retrieval-Augmented Generation).
• Goal: Building systems that can reason and act, not just predict.

2. 🏗️ System Design for AI

Architecting scalable and reliable ML systems.

• Focus Areas: Distributed training patterns, inference optimization, vector database scaling, and MLOps pipelines.
• Perspective: applying rigorous system design principles to ML infrastructure.

3. 🧩 Algorithmic Foundations (DSA & Math)

The mathematical and logic backbone of efficient software.

• Focus Areas: Graph algorithms, dynamic programming, and optimization techniques relevant to AI.
• Implementations: Solutions often provided in both Python (for prototyping) and C++ (for performance).

🛠️ Tech Stack

• Languages: Python, C++
• Frameworks: PyTorch, TensorFlow, LangChain (or similar Agentic frameworks)

🚀 Getting Started

To run the examples in this repository, clone the repo and install the necessary dependencies:

git clone [https://github.com/Parihar07/Ml_AI_Practice.git](https://github.com/Parihar07/Ml_AI_Practice.git)
cd Ml_AI_Practice
pip install -r requirements.txt
# For C++ components, refer to the specific sub-folder Makefiles.