Large language models, RAG, agents, and prompt engineering
LLM training pipeline, tokenization, sampling strategies, RAG introduction, and AI agents overview
Master zero-shot, few-shot, and chain-of-thought prompting techniques, structured output, and prompt security
Advanced RAG architecture including chunking, vector databases, retrieval strategies, and evaluation
When and how to fine-tune with LoRA, QLoRA, PEFT, dataset preparation, and deployment considerations