Scholar
Roman Lutz
Google Scholar ID: joujH5UAAAAJ
Responsible AI Engineer at Microsoft
Citations & Impact
Citations
870
H-index
8
i10-index
7
Publications
11
Co-authors
0
Publications
Resume
Academic Achievements
- January 2025: Published a whitepaper titled 'Lessons Learned from Red Teaming 100 Generative AI Products'
- July 2024: PyRIT was a key part of Phi-3 Safety Post-Training
- May 2024: Attended the Microsoft //Build conference to talk about PyRIT
- February 2024: Released PyRIT and expanded its capabilities for multimodal generative AI systems
- October 2023: Published a paper on ArXiv titled 'A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications'
- August 2023: Fairlearn paper published in the Journal for Machine Learning Research (Open Source Software section)
- December 2021: Released the Responsible AI dashboard
Background
- Responsible AI Engineer at Microsoft and open source maintainer. Focuses on identifying vulnerabilities of generative AI systems in terms of AI safety and security.
Miscellany
- Interests include open source project maintenance and technical sharing