Technical AI Safety
Explore cutting-edge research in interpretability, scalable oversight, and alignment benchmarks. Connect with researchers pushing the boundaries of AI safety.
September 27, 2025 · ETH Zurich
Join 200+ researchers, engineers, students, and professionals from Zurich's tech ecosystem for a one-day conference on AI Safety.
Learn from technical pioneers, engage with governance experts, and discover opportunities to contribute.
Free to attend—request your spot.
Speaker lineup and detailed schedule coming soon
Explore cutting-edge research in interpretability, scalable oversight, and alignment benchmarks. Connect with researchers pushing the boundaries of AI safety.
Navigate the policy landscape, regulatory frameworks, and governance mechanisms essential for responsible AI deployment at scale.
Discover success stories, funding pathways, and talent pipeline development. Find your path in the growing AI safety ecosystem.
Engage with thought leaders across technical research, governance, and field-building tracks. Sessions designed for all expertise levels.
Connect with 10+ leading AI safety organizations eager to meet potential collaborators, researchers, and team members.
Participate in carefully designed activities that match you with peers, mentors, and hiring teams based on your interests.
Switzerland leads global talent rankings and hosts 7 of the world's 10 leading AI companies including Google, Meta, Microsoft, and now Anthropic and OpenAI. With the highest AI engineer density in Europe and world-class institutions like ETH Zurich, it's becoming a natural hub for advancing AI safety research.
ETH Zurich stands as one of the world's leading universities for technology and science. Home to 21 Nobel Prize winners, including Albert Einstein, ETH combines 170 years of academic excellence with cutting-edge research facilities.
Detailed room assignments and venue logistics will be announced closer to the event.