About
Tassilo Henninger is a PhD researcher at the Data Science and Text-based Information Systems (DATEXIS) group at the Berliner Hochschule für Technik (BHT). He is supervised by Prof. Dr. Alexander Löser and joined the group in September 2026. His research focuses on reasoning and post-training in large language models, particularly process reward models and verifiable rewards.
Before his PhD, he spent over ten years at Boehringer Ingelheim. He started as a dual student and moved from data engineering to data science, where he built agentic systems, retrieval pipelines, and RAG applications. He holds an M.Sc. in Data Science from BHT and a B.Sc. in Business Informatics from DHBW.
In his free time, he goes bouldering and climbing and has a deep love for electronic music.
Education
- Master of Science, Data Science, University of Applied Sciences Berlin (BHT)
- BA Applied Science, Business Informatics, Baden-Wuerttemberg Cooperative
Research Interests
- Large Language Models
- LLM Reasoning
- Post-training and Alignment
- Reinforcement Learning for LLMs
Technical Skills & Methods
- Foundational Large Language Model post-training
- Reinforcement Learning with Verifiable Rewards (RLVR)
- Supervised Fine-Tuning
- Reasoning model training
- Information Retrieval