Home

Hello! I am currently working as part of Anthropic’s Frontier Red Team, where I focus on evaluating large language models’ (LLMs’) cyber capabilities to help ensure their safe and robust development. This role combines my background in cybersecurity with my research in machine learning, allowing me to contribute to the critical work of making advanced AI systems safe, reliable, and aligned.

Before joining Anthropic, I completed my PhD at Carnegie Mellon University (CMU) studying under my advisor, Lujo Bauer, in CyLab. At CMU, my projects involved machine learning for malware detection, cooperative multi-agent reinforcement learning, robust machine learning, and machine learning based anomaly detection. I usually incorporate my interest in reinforcement learning into my research whenever I get the chance!

Originally from the Matanuska Valley in Alaska, I graduated from the United States Air Force Academy (class of 2014) with a BS in Computer Science and from Carnegie Mellon University, Information Networking Institute with an MS in Information Security. After gaining valuable experience serving in unique roles in the Air Force, I separated as a Captain (O3) to pursue a PhD supported by the NDSEG Fellowship.

My current focus is on advancing the safe and responsible development of advanced AI systems, particularly in eliciting, evaluating, and projecting LLM’s cybersecurity capabilities.