Course Objectives: Upon completion of the course, students will be able to: Understand and explain the core concepts of Gen Ai: embeddings, architectures, training and inference used by large language models (LLMs). Analyse the capabilities and limitations of Gen AI technologies across domains. Design, develop and evaluate AI solutions using techniques such as retrieval-augmented generation (RAG) and prompt engineering. Implement generative AI workflows using recent tools and platforms, including language model APIs and open-source frameworks. Develop agentic flows that combine LLMs with tools and structured reasoning to perform complex tasks. Identify ethical challenges associated with Gen AI and develop strategies to mitigate risks in real-world applications. Competencies Understand the principles of Generative AI, including embeddings, architectures, training and inference workflows of large language models (LLMs). Explain how transformer-based models process and generate natural language. Evaluate the strengths and limitations of Gen AI tools across use cases and domains. Use prompt engineering techniques and LLM hyperparameters to guide and control the behaviour of LLMs effectively. Design and implement retrieval-augmented generation (RAG) pipelines to improve response relevance. Integrate LLMs into software applications using APIs and open-source frameworks. Develop agentic workflows where LLMs perform reasoning and interact with external tools or environments. Develop Gen AI solutions using platforms such as LangChain or similar libraries. Apply principles of responsible AI by identifying and addressing issues related to bias, misuse, and transparency. Communicate the value, risks, and strategic potential of Gen AI to technical and non-technical stakeholders.