Yannik Käckenmeister

Building backend infrastructure for intelligent document processing—including inter-service communication, caching, persistence layers, and API design.

Conducted research and development on indexing structures generated by neural retrievers in RAG systems. Concluded with a one-month transition period focused on project handover, while completing my master's degree, before transitioning to a full-time role.

Extended my bachelor's thesis research on 3D object recognition, continuing development and eventually co-publishing key results.

Built microservices to process and analyze vehicle data from test drives.

Developed new features for the “4EM” modeling software and supported teaching as a tutor and by checking preliminary exam work.

Grade: very good | Thesis: "Sparse Index Structures in RAG Systems: Efficient Search and Embedding Strategies for Heterogeneous Data Sets"

Grade: very good | Thesis: "Identification, Evaluation and Adaption of Neural Network Based 3D Object Detection Methods for Underwater Environments"