AI Researcher &
ML Engineer

I'm a highly driven ML researcher and engineer with expertise in AI safety, LLM evaluation, and multi-agent systems. My research focuses on understanding and improving the behavior of large language models in complex scenarios.

Research Interests

AI Safety & Evaluation Large Language Models Multi-Agent Systems Natural Language Processing Adversarial Robustness Machine Learning Systems
View Publications Contact Me
David Guzman Piedrahita

Currently at

University of Zürich
MSc Computer Science

ETH Zurich & Max Planck Institute
Research Assistant

Publications & Research

Experience

Research Assistant

ETH Zurich & Max Planck Institute for Intelligent Systems Sep 2025 - Present
  • Developing multi-agent LLM systems to study the emergence and evolution of sanctioning norms in cooperative social dilemmas
  • Building a multi-environment benchmark incorporating game-theoretic scenarios to systematically analyze how punishment and reward mechanisms influence cooperative behavior
  • Funding proposal writer & co-designer; project funded by the AI Safety Fund ($499,838, 2025–2026)

Research Assistant

University of Zürich Mar 2024 - Aug 2024
  • Fine-tuned large scale LLMs on Cerebras chips
  • Improved domain-specific performance by 68% for Switzerland-specific knowledge
  • Developed LLM chatbot with highly specific local knowledge

Research Assistant

ETH Zurich Sep 2023 - Feb 2024
  • Conducted large-scale web scraping initiatives, storing millions of PDFs in PostgreSQL databases
  • Reduced HTML extraction time by 43% by prioritizing direct extraction from URLs over browser simulation
  • Coordinated with cross-functional teams to maintain clean coding practices, thorough documentation, and version control via Git

Get In Touch

Open to opportunities in AI safety research, LLM evaluation, and multi-agent systems!

davidguzman1120@gmail.com LinkedIn GitHub