LLM ENGINEERING AND GENERATIVE-AI

What Will You Learn?

• Understand how large language models work, from tokenization to attention and generation
• Write effective prompts and design reliable instructions for LLM applications
• Work with both closed-source LLM APIs and open-source models running locally with Ollama
• Build retrieval-augmented generation (RAG) systems, from basic pipelines to advanced retrieval techniques
• Use embeddings and vector databases to power search and retrieval
• Fine-tune large language models efficiently using LoRA and QLoRA
• Build AI agents that call tools and reason through multi-step tasks
• Design multi-agent systems using agent orchestration frameworks
• Evaluate, test, and deploy LLM applications for real-world use
• Build a complete, end-to-end generative AI application