Foundations of Generative AI & Reasoning Systems

1 Unit · Graduate

This course provides a hands-on introduction to the science and algorithms behind today's Large Language Models (LLMs) and agentic AI. Architecture, training, and deployment of transformer-based models. Prompt engineering (including algorithmic approaches), and post-training with reinforcement learning methods such as RLHF and direct preference optimization for alignment and safety. The course also covers large reasoning models, in-context learning, and agentic AI state-of-the-art (architectures, memory, context engineering). Focus on practical implementations using modern software techniques and understanding the science of LLMs and agents.