I am a senior researcher in the Language and Conversation Group at IBM Research, focusing on the evaluation, safety, and security of large language models and AI agents. My work examines how AI systems make decisions, express preferences, and behave in complex or adversarial settings, with an emphasis on developing methods for assessing reliability, alignment, and risk.

I also teach in the Computer Science faculty at the Academic College of Tel Aviv-Yaffo, where I lead both introductory and advanced machine learning courses.

I earned my bachelor's degree in computer engineering from the Technion, followed by a master's at Tel Aviv University, where I worked with Prof. Dana Ron and Dr. Raid Saabni on a thesis about online handwriting recognition in Arabic. For my Ph.D. in computational neuroscience at Haifa University’s Sagol Department of Neurobiology, I studied cognitive models of attention and motivation, focusing on how the brain represents different states, under the guidance of Dr. Genela Morris.

Research Interests: 

My research interests are mainly focused on the foundation of learning mechanisms, encompassing both artificial and natural systems, including:

Natural Language Processing - Large Language Models - Generative Models - AI Safety - Computational Neuroscience - Cognitive Modeling - Reinforcement Learning.