CodeCrafts | Hands-On GPT: From Training to Deployment

What is it?

Understanding how GPT models work requires more than just theory—it’s about building, training, and deploying them yourself. This hands-on workshop will take you step by step through the process of creating a Generative Pretrained Transformer (GPT) from the ground up.

Through practical coding exercises, we will guide you through the fundamentals of machine learning, transformer architecture, and tokenization while you get to prepare and train your own model. Beyond training, we’ll explore how to integrate GPT into applications, ensure secure and responsible deployment, and implement monitoring for performance optimization.

This workshop isn’t just about following a tutorial—it’s about developing a deeper understanding of how modern language models work and how to apply them effectively. Whether you’re new to transformers or looking to refine your skills, this session will give you the practical experience and confidence to build and deploy your own GPT model.

Keno Dreßel

Specializing in artificial intelligence and machine learning, Keno focuses on integrating AI into full-stack applications to create intelligent, data-driven solutions. With a background in IT and Cognition from the University of Copenhagen, Keno combines technical depth with hands-on experience in software engineering. At SQUER, he helps teams apply AI effectively, sharing his knowledge through consulting, workshops, and training.

Alfred Feldmeyer

Alfred has a strong background in DevOps automation, cloud technologies, and artificial intelligence. He has worked on a wide range of projects, from train control systems at Deutsche Bahn to autonomous driving at Fraunhofer IKS. With experience in AI research at Siemens and a deep curiosity for solving complex problems, Alfred combines an engineering mindset with a passion for elegant and efficient solutions. At SQUER, he focuses on applying AI to enhance software development and architecture.