📌 AI Engineering
🎯 Goal:
Gain hands-on experience in deploying, fine-tuning, and integrating AI models into applications.
1️⃣ AI Development Basics
- Running AI models locally (Mistral, Ollama) - Ollama Docs
- Using LLM APIs for development (OpenAI, Replicate) - Replicate API Docs
- Fine-tuning vs. RAG (Retrieval-Augmented Generation) - LangChain RAG Guide
2️⃣ AI Infrastructure & Scaling
- Self-hosted AI vs. Cloud AI (AWS, GCP) - AWS AI Services | GCP AI Services
- Optimizing AI for Performance (GPU vs. CPU) - NVIDIA AI Optimization
- AI Model Compression & Quantization - TensorFlow Model Optimization
🎯 Hands-on Tasks
- Deploy a self-hosted LLM chatbot
- Experiment with RAG using LangChain
- Integrate AI-powered recommendations into a web app