Omer Hofman is a Principal AI Security Researcher focused on evaluating and securing large language model systems in real-world deployments. His work centers on LLM red teaming, vulnerability scanning, guardrail design, and policy compliance in agentic AI systems. He leads research on practical methods for measuring model robustness, improving evaluator reliability, and translating AI security theory into deployable engineering solutions. His recent work explores how evaluation pipelines themselves can become a hidden source of risk, and how to design systems that produce trustworthy security signals at scale.
linkedin.com/in/omer-hofman-86688a192/
