Developed the initial scaffolding for a machine learning project in the Julek-AK/AE2224-I-B04 repository, focusing on creating a scalable foundation for future experimentation in Bayesian deep learning, deep neural networks, and hidden Markov models. Established a clear directory structure and included bootstrap artifacts such as placeholder test.py files to streamline subsequent development and onboarding. The work emphasized maintainability and rapid prototyping, leveraging Python for project organization and version control with Git. By setting up this modular architecture, the developer enabled consistent workflows and simplified the process for future contributors to extend or test new machine learning approaches across multiple domains.