Christian Nickel

Christian Nickel

Computer Scientist and Researcher @ RC-Trust. Exploring AI-Reasoning, -Safety, -Security and its intersection with Human Behavior. Passionate about both progress and safety in the agentic age, incorporating multidisciplinary approaches to push the boundaries of AI and its applications.

About

Who I Am

I am Chris — a Computer Scientist and AI Researcher, currently working as a full-time researcher at the Research Center Trustworthy Data Science and Security (RC-Trust) and the University of Duisburg-Essen, in the Human Understanding of Algorithms and Machines (HUAM) group. My work there investigates shifts in human strategic behavior in economic games when facing AI opponents.

In a parallel project with Dr. Florian Mai (University of Bonn), I investigate the steerability of LLM agents with respect to predefined rules and properties in social environments — analyzing how targeted interventions shape model reasoning and subsequent behavior. A preprint will be available soon.

Research Journey

My path toward AI-Safety and human–AI interaction grew through a series of research experiences that each deepened my understanding of what makes AI trustworthy.

During and after my Master’s in Computer Science at the University of Bonn, I worked at the Data Science & Language Technologies Group (CAISA Lab), Bonn-Aachen International Center for Information Technology (b-it), University of Bonn, advised by Prof. Dr. Lucie Flek, focusing on Reasoning Chains and Faithfulness in LLMs. Together with Laura Schrewe, I developed a novel benchmark of perturbed Theory of Mind (ToM) tasks and metrics for AI reasoning correctness — work that earned us the Best Poster Award at WiNLP @ EMNLP 2024 in Miami, FL, USA. A follow-up paper was presented at the ToM4AI Workshop @ AAAI 2025 (PDF, OpenReview), and an extended version probing reasoning robustness is now available as a preprint.

Before my PhD, I worked as a Research Assistant at the Fraunhofer Institute for Applied Information Technology (FIT) on Distributed Ledger Technology (DLT/Blockchain) and Self-Sovereign Identity (SSI) solutions, with a focus on usability and interoperability. During my studies at Bonn, I also served as a Teaching Assistant for the “Human-Computer Interaction” course under Prof. Dr. Matthew Smith and the “Data-Centric Computer Science” course under Prof. Dr. Christian Bauckhage.

Earlier projects include RansomDenied, a user-centered ransomware-resistant backup system, and my Bachelor’s thesis on the privacy compliance of smart cameras across different jurisdictions — analyzing network traffic and evaluating GDPR conformity.

Education

  • M.Sc. in Computer Science — University of Bonn (2021 – 2024) Focus: Artificial Intelligence, Machine Learning, Cybersecurity
  • B.Sc. in Computer Science (Psychology minor) — University of Bonn (2017 – 2021) Focus: Cybersecurity, Usable Security, Artificial Intelligence

Awards & Recognition

Beyond Research

I am passionate about approaches that merge disciplines and push the boundaries of what we understand — in and outside of research. Some things I find myself thinking about, exploring or building in my spare time:

  • FOSS Smart Home — a self-hosted, privacy-preserving stack centered on Home Assistant
  • Hi-Fi and Acoustics — the bridge between physical properties of sound and human perception: Why does a speaker sound “warm” or “slow”, and what does that mean in measurable quantities?
  • Astronomy and Physics — exploring the cosmos at large and niche corners of physics like Bohmian Mechanics
  • Historical Technology and Engineering — from ancient architecture to early engineering marvels (Vitruvius’ De Architectura sits on my shelf — waiting for someone else to also notice it…)
  • Exploring Places — on foot, eMTB, or road trip: lively cities, abandoned monasteries, deserted landscapes, and everything in between

Chris at the Grand Canyon

Sic luceat lux.