Large Language Models (LLMs), such as GPT, Claude and Llama, are powerful tools that have transformed the landscape of Natural Language Processing (NLP), enabling advanced applications in various fields. The “Building Large Language Model Applications,” course is a practical, hands-on course designed to provide students with in-depth knowledge and experience in developing applications utilizing LLMs. Throughout the course, students will work on real-world projects and learn how to design, implement, and deploy advanced LLMs systems.
| Type | Lab (advanced level) |
| Term | SS 2026 |
| Mentor(s) |
Stefan Decker |
| Assistant(s) |
Yongli Mou Yixin Peng Er Jin daham.mohammed.mustafa@fit.fraunhofer.de |
The course schedule will be announced soon, once all the students joined the RWTH Moodle Room.
For this Lab, full in-person participation is required. Please note the following rules and expectations:
Mandatory Meetings (in-person):
You must attend all collective meetings on site — including the Kick-Off Meeting, the Mid-term Meeting, and the Final Presentation. Exceptions are possible only in special cases (e.g., illness or urgent personal matters). In such cases, you must either provide official documentation (e.g., a medical certificate from doctor) or notify us in advance with a reasonable explanation.
Weekly Work Commitment:
Once the project begins, you are expected to dedicate at least 1.5 full working days per week (approx. 8 hours per day, namely 10-12 hours in total per week) to your project. Group meetings can be held online if your team agrees. However, if your supervisor requests an in-person meeting, you must be able to adjust your schedule to attend on site.
Communication & Collaboration:
After the Kick-Off Meeting, we will provide a Discord channel for each group. Please use this channel actively to stay in touch with your teammates and your supervisor. It is important that you remain reachable and avoid situations where you cannot be contacted for more than a week.
Weekly Group Meetings:
Each group is required to hold regular internal weekly meetings to discuss progress and coordinate tasks. Weekly meetings with your supervisor are not mandatory; the frequency of these meetings will be agreed upon between your group and your supervisor after the teams are formed.
Learning Objectives:
By the end of this course, students will be able to:
– Understand the architecture and the core principles behind LLMs and their applications.
– Effectively preprocess and prepare data for training LLMs.
– Develop and fine-tune LLMs for specific use cases.
– Build a single LLM-Based Agent / LLM-based workflow / Multi-agent System for specific purpose.
– Build and deploy robust applications utilizing LLMs.
– Address ethical considerations and implement best practices in the development of LLM applications.
– Basic knowledge of machine learning and natural language processing.
– Basic knowledge of software engineering.
– Proficiency in programming, particularly in Python.
– Familiarity with machine learning frameworks such as TensorFlow or PyTorch is recommended.
– Familiarity with LLM and LLM-based agentic system is recommended.