Master’s theses: LLM/VLM-assisted PCB design with KiCad and related EDA tools

30.09.2026, Diplomarbeiten, Bachelor- und Masterarbeiten

We are offering Master’s theses focused on integrating Large Language Models (LLMs) and Vision-Language Models (VLMs) into PCB design workflows using KiCad. The goal is to develop AI agents that automate repetitive engineering tasks, such as datasheet analysis, component placement, and layout validation. Ideal candidates should have strong programming skills (Python/C++), a basic understanding of electronics, and ideally, a background in machine learning.

The latest developments in the field of large language models (LLMs) and vision-language models (VLMs) highlight the increasing relevance of AI for complex engineering processes. In PCB design with tools such as KiCad, many recurring tasks arise: reading and structuring datasheets, generating symbols, footprints and netlists, planning component placement, making routing decisions, reviewing ERC/DRC messages, and coordinating between hardware, software and manufacturing teams. Our goal is to integrate AI agents into existing PCB workflows so that they can support simple to moderate intellectual tasks and increase the overall performance of the organisation consisting of humans and AI agents. In doing so, the immediate benefit for the individual engineer should remain in focus.

The following fields of research are open to you for your work in the context of LLM/VLM-assisted PCB design:

• Communication between AI agents in PCB workflows, for example between schematic, layout, component and verification agents
• Tool integration in EDA environments, especially KiCad through Python APIs, scripting, file formats such as netlists, Gerber files and KiCad project structures, as well as plug-ins
• Techniques for fine-tuning, retrieval and evaluation of LLMs/VLMs for PCB-specific domain knowledge
• VLM-based analysis of schematics, PCB layouts, assembly drawings, renderings, Gerber previews and error messages
• Automated generation and validation of component models, constraints, layout recommendations and design checks

We offer:

• An exciting and future-oriented research environment at the intersection of electronics, EDA tools and modern AI
• Work with open-source EDA tools such as KiCad and open file formats
• Writing in German or English possible

Requirements:

• Initiative and a creative, problem-solving mindset
• Advanced knowledge of Python, C++ or a comparable language
• Basic understanding of electronics, circuits and PCB workflows; knowledge of KiCad or other EDA tools is an advantage
• Knowledge in machine learning, especially large language models, vision-language models or agentic systems, is an advantage
• Willingness to learn about technical EDA workflows, datasheets, design rules and standards

Are you interested in this topic or do you have questions?
Feel free to contact André Schamschurko (andre.schamschurko@tum.de)
TUM Chair of Robotics, Artificial Intelligence and Real-time Systems

Kontakt: andre.schamschurko@tum.de