Willem Röpke
      
          I'm seeking a research scientist or post-doc role in reinforcement learning, LLMs, planning, or other ambitious ML projects.
      Final-year PhD researcher at the Vrije Universiteit Brussel, working on reinforcement learning, multi-objective decision making & LLM post-training.
      
    
    
      Experience
      
        - 
          
2021 - present
          PhD Candidate
          Vrije Universiteit Brussel (VUB), 
AI Lab 
          Multi-objective RL; teaching assistant for the machine learning course.
         
        - 
          
Mar 2025 - May 2025
          Research Visitor
          University of Oxford, 
FLAIR 
          RL post-training for large language models.
         
        - 
          
Nov 2022 - Dec 2022
          Research Visitor
          University of Galway
          Distributional MORL; joined the research group of Prof. Patrick Mannion.