What the course covers.
- Module 1
Foundations of LLMs & Generative AI
Learners start by understanding how large language models operate, including transformer architecture, attention mechanisms, tokenisation, and embeddings. This module balances theory and practice, helping learners grasp the underlying mechanics of LLMs while preparing them for hands-on experiments with pre-trained models.
- Module 2
Prompt Engineering & Fine-Tuning
This module focuses on practical skills for getting the most out of LLMs. Learners explore prompt design, few-shot and zero-shot learning, and techniques for fine-tuning models to specific tasks. Hands-on exercises include building custom chatbots, text summarisation tools, and other generative AI applications that can be deployed in real-world scenarios.
- Module 3
Applications, Deployment & Ethics
Learners apply their knowledge to design and deploy generative AI systems responsibly. The module covers deployment best practices, integration into applications, model evaluation, and mitigating risks such as bias, hallucination, and misuse. Ethical and regulatory considerations are emphasised, preparing learners to develop AI that is both effective and trustworthy.
