May 2026 – present
Frontier Security Researcher
Institute for AI Policy and Strategy
- Researching cyber risks from advanced AI and safeguards for the use of AI in government
Curriculum vitae
Positions & Education
Jan 2026 – Apr 2026
Winter Fellow in AI Governance
Centre for the Governance of AI
- Researching honeypots against AI Agents under mentorship of Alan Chan and Jam Kraprayoon
Jun 2024 – Oct 2025
PhD candidate in AI Safety
CISPA Helmholtz Center for Information Security
- Researching LLM Alignment and Interpretability advised by Prof. Mario Fritz
- Coadvised by Prof. David Krueger at MILA as part of the ELLIS PhD program
Sep 2021 – Nov 2023
MSc Computer Science – AI Technology Track
Delft University of Technology
- Thesis: Counterfactual Explanations of Learned Reward Functions
- Grade: 8.5/10
Apr 2017 – May 2021
BSc Business Informatics
Otto-Friedrich-University Bamberg
- Thesis: Efficient inference of qualitative temporal information for robust planning
- Grade: 1.2 (cum laude)
Research experience
Jan 2024 – May 2024
Participant
AI Safety Camp
- Conducted and published research to characterize and prevent harmful fine-tuning attacks
Jul 2022 – Aug 2022
Research Fellow
Swiss Existential Risk Initiative
- Employed interdisciplinary thinking to identify data requirements for Inverse Reinforcement Learning to learn human values
- Experimentally validated theoretical shortcomings and technical challenges for Reward Learning
Jun 2021 – Aug 2021
Research Assistant
Otto-Friedrich-University Bamberg
- Conducted empirical research on knowledge representation in temporal domains
Teaching & Organising
Nov 2022 – Dec 2023
Founder
Delft AI Safety Initiative
- Devised strategy and structure for a new student organisation focused on addressing risks from AI
- Delivered courses and regular events on AI Alignment to >50 students
- Presented introductory talks about research in AI Safety
2019 & 2021
Teaching Assistant – Algorithms and Data Structures
Otto-Friedrich-University Bamberg
- Held weekly classes and discussions explaining key concepts in Computer Science
- Graded assignments and provided feedback
Publications
- Detecting Offensive Cyber Agents: A Detection-in-Depth Approach
IAPS Report, 2026 - Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
TMLR, 2025 - Position: Safety Must Precede the Deployment of Open-Ended AI Agents
ICML 2026 - Representation Noising: A Defence Mechanism Against Harmful Finetuning
NeurIPS, 2024 - Immunization against harmful fine-tuning attacks
Findings of EMNLP, 2024 - Explaining Learned Reward Functions with Counterfactual Trajectories
AIEB workshops at ECAI, 2024 - On robust vs fast solving of qualitative constraints
Journal of Heuristics, 2023