October 16, 2025—The Software Engineering Institute (SEI) invites AI researchers, engineers, and practitioners to attend Engineering Safety-Critical AI Systems, an Association for the Advancement of Artificial Intelligence (AAAI) 2025 Fall Symposium. The symposium will be held in Arlington, Virginia, November 6-8. Registration is open now.

AI has increasing application in high-risk settings, but few foundational practices exist for engineering safe AI systems, and research in safety engineering for AI remains scattered across disparate fields of study. The symposium will address the fundamental question, How should we build AI systems for safety-critical applications?

AI experts will present papers and participate in panel discussions on topics that include

• moving AI research to AI safety engineering
• identifying and mitigating AI hazards
• industry perspectives on AI safety

Keynote speakers will include Thomas Dietterich, distinguished professor emeritus and associate director of policy at the Collaborative Robotics and Intelligent Systems Institute, Oregon State University; Laura Freeman, deputy director, Virginia Tech National Security Institute; Benjamin Grosof, program manager in the Defense Sciences Office, Defense Advanced Research Projects Agency (DARPA); and Patrick Hall, teaching assistant professor of decision sciences, George Washington University.

Matt Gaston, director of the SEI’s AI Division, will discuss the SEI’s work on an ongoing national study of AI Engineering.

The SEI is organizing the event in collaboration with researchers from CrowdStrike, MIT Lincoln Laboratory, Duke University, Johns Hopkins University, Carnegie Mellon University, the University of Virginia, the University of Maryland, and the University of California, Berkeley.

Learn more about the Engineering Safety-Critical AI Systems 2025 symposium, part of the AAAI 2025 Fall Symposium Series, and register to attend.