• Understand the fundamentals of Large Language Models (LLMs)
• Integrate LLMs purposefully into applications and workflows
• Learn essential techniques for optimization and automation
• Gain insight into initial steps for scaling LLM‑based solutions
• Become familiar with production‑oriented aspects of LLM usage

Combination of theoretical foundations and hands‑on exercises

Introduction to Large Language Models (LLMs)

• History of LLMs
• Major providers
• Typical application scenarios

Developing LLM‑Based Applications

• Prompt engineering
• Fine‑tuning
• Domain adaptation

Workflows and production‑oriented aspects

• Retrieval‑Augmented Generation (RAG)
• Use of agents
• Automation
• Basic concepts of MLOps

• Develop and optimize applications and workflows using LLMs.
• Effectively utilize frameworks like LangChain and Transformers.
• Customize LLMs to meet specific requirements, e.g., through fine-tuning.
• Automate workflows and extend them with retrieval-augmented generation (RAG).
• Use tools for monitoring, testing, and scaling.
• Deploy LLMs securely and efficiently in production.

• A comprehensive introduction to the world of LLMs, specifically designed for beginners.
• Practical exercises for developing LLM-based applications.
• Expert knowledge on frameworks and tools like LangChain, RAG, and MLOps.
• Support from experienced instructors and practice-oriented content.
• The opportunity to integrate cutting-edge technologies into your projects.

Dorian Knoblauch is a research associate in the Critical Systems Engineering group at the Fraunhofer Institute FOKUS. His work focuses on the development and assurance of safety‑critical software systems. He has more than five years of professional experience in the field of machine learning and has published several scientific papers on topics such as ML, the auditing and verification of AI systems, and IT security. In addition, he is a trainer at the Fraunhofer Academy, where he conducts courses on machine learning, security, and testing.

Who is the LLM (Basic) training suitable for?

The LLM training is aimed at beginners with basic programming knowledge and developers who want to integrate Large Language Models into their applications and workflows in a practical way. Basic knowledge of Python and system installation is required.

What prior knowledge do I need for the LLM fundamentals?

Basic Python skills and general technical understanding (e.g., setting up development environments) are sufficient. Advanced AI experience is not necessary (Basic level).

What exactly will I learn in the LLM Development (Basic) course?

You will receive a compact introduction to LLMs (history, providers, use cases) and learn prompt engineering, fine‑tuning/domain adaptation, Retrieval‑Augmented Generation (RAG), agent‑based automation, and MLOps fundamentals—with practical relevance.

What is prompt engineering and why is it important?

Prompt engineering is the targeted design of inputs for an LLM to achieve more precise, consistent, and cost‑efficient results. It is a central tool in LLM development and part of the course content.

Does the LLM training cover RAG (Retrieval‑Augmented Generation)?

Yes. The course explains how RAG works and how to connect your own data sources to improve response quality and contextual relevance.

Is fine‑tuning covered in the LLM training?

Yes. You will learn the fundamentals of fine‑tuning and domain adaptation, including classification, use cases, and quality considerations—providing orientation for further steps.

Does the course also cover workflows, agents, and automation with LLMs?

Yes. The training covers LLM workflows, agent concepts, and automation to help you move from individual prompts to stable processes.

What does the MLOps section of the LLM (Basic) training include?

You will receive foundational MLOps knowledge for production‑oriented usage: basic principles for stability, scaling, and operation of LLM‑based applications.

How practice‑oriented is the LLM training?

The course combines theoretical foundations with hands‑on exercises so you can directly apply what you learn to your own projects.

In which format is the LLM training offered—and in which language?

The training can be delivered on‑site, online, or in‑house and is available in German or English (Basic level, duration: 2 days).

What goals do I pursue with the LLM fundamentals training?

The goal is to classify LLMs reliably, understand best practices (e.g., prompt engineering), and design initial LLM prototypes & workflows—forming the foundation for further LLM development.

Which roles benefit most from the LLM training?

Especially developers, technical beginners, and IT professionals who want to integrate LLMs into applications or automate workflows—at Basic level with a clear practical focus.