$ whoami
I build and align large language models — and the tools that train them.
Düsseldorf, Germany
scrollResearch scientist and engineer specialising in reinforcement learning post-training and LLM alignment. I work on model trustworthiness, uncertainty quantification, and hallucination reduction — bridging rigorous mathematical theory and production-level engineering through scalable, reliable, and modular training frameworks.
I hold a PhD (magna cum laude) in computer science from Heinrich Heine University Düsseldorf, where I also worked as a postdoctoral researcher on reinforcement learning post-training and LLM alignment. With 10+ years across academia and industry, my work spans publications at NeurIPS, ACL, and EMNLP — and the open-source tooling that made them possible.
Reinforcement learning and multi-agent coordination for long-horizon decision making in agentic dialogue and tool-using systems.
Reinforcement learning methods for aligning large language models using intrinsic and self-supervised reward signals, reducing reliance on external human preference data.
Reproducible, configurable, and distributed training systems enabling rapid experimentation across HPC and cloud environments.
Bayesian and distributional methods for uncertainty estimation, calibration, and robustness — applied to trustworthy and controllable AI systems.
$ tail -n 4 ~/highlights.log
"Less is More: Local Intrinsic Dimensions of Contextual Language Models" — using the geometry of contextual embeddings to study LLM training dynamics and generalisation.
"Post-Training Large Language Models via Reinforcement Learning from Self-Feedback" — using the model's own confidence as an intrinsic reward, no human feedback required.
"A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction" — confidence-driven active learning and label validation for sequential multi-output tasks.
Dissertation "Uncertainty Estimation, Management, and Utilisation in Human-Computer Dialogue" defended at Heinrich Heine University Düsseldorf.
$ git log --oneline --career
bd93f9 (HEAD -> now)
Mar 2024 → Jun 2026 · Düsseldorf, Germany
ff79c6
Jul 2019 → Mar 2024 · Düsseldorf, Germany
8be9fd
Jun 2018 → May 2019 · Pretoria, South Africa
Configuration-driven deep learning experiment launcher
Open-source experiment launcher unifying Facebook Hydra, Hugging Face Accelerate, and the UV workflow. One config launches anything from a local debug run to multi-GPU distributed training on SLURM clusters or SkyPilot-managed cloud — no code changes between backends.
Reinforcement Learning from Self-Feedback
Post-training method that uses a language model's own confidence as an intrinsic reward signal — aligning LLMs and improving calibration and reasoning without external human preference labels.
Multi-agent RL for long-horizon agentic systems
Coordinated decision-making between router and expert agents with explicit credit assignment. Write-up in progress.
selected work — NeurIPS · ACL · EMNLP · TACL
Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik, Hsien-chin Lin, Milica Gašić
Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Milica Gašić
Benjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck, Renato Vukovic, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Bastian Rieck, Marcus Zibrowius, Milica Gašić
Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Milica Gasic
University of Pretoria · 2013–2015 · Pretoria, South Africa
University of Pretoria · 2016–2016 · Pretoria, South Africa
University of Pretoria · 2017–2018 · Pretoria, South Africa
Statistical learning, data analytics and visualization.
Heinrich Heine University · 2019–2024 · Düsseldorf, Germany
Magna cum laude. Thesis: Uncertainty Estimation, Management, and Utilisation in Human-Computer Dialogue.