Language Models in Practice: Using LLMs Safely, Efficiently, and Locally
Course goals
This microcredential provides a comprehensive and practice-oriented introduction to Large Language Models (LLMs). Participants will gain foundational knowledge of LLM architectures, training methods, and application scenarios - from general use cases to secure, local deployments. Through hands-on exercises they will learn effective prompting techniques, work with open-source frameworks, and explore methods to enhance model efficiency and ensure safe operation. The course bridges theory and real-world application, preparing students and professionals to use LLMs responsibly and effectively in both academic and business contexts.
Course implementation
A total of 60 working hours is targeted.
The synchronous online sessions are planned on 13./27.11.2025, 11.12.2025 and 08./15./22.01.2026, 01:45 p.m. each day.
The course is offered by the Professorship for Artificial Intelligence of the Department of Computer Science.
As this is a conceptual course within the TUCacademy program, some aspects are subject to change.
Requirements and examination
Nevertheless, good Python programming skills are required. Basic knowledge on deep neural networks is advantageous. The course language is English.
The course will grant 2 ECTS when passing the exam.
Das Lernangebot ist im Rahmen des Projektes "TUCacademy: Flexible Lernpfade für arbeitsmarktrelevanten Kompetenzerwerb und Future Skills" entstanden. Das Projekt wird finanziert durch den Europäischen Sozialfond und den Freistaat Sachsen.