As Staff Security Architect at ZioSec, Alex led the design and execution of the company’s Adversarial Testing Platform for AI Agents, a system that continuously orchestrates hundreds, soon thousands, of automated controlled attacks on AI agents to validate the effectiveness of their safety guardrails. Alex’s research has made him one of the foremost practitioners in adversarial testing of generative and agentic AI. He was the principal architect behind ZioSec’s red-team automation framework, which operationalizes what enterprises have long struggled to do: continuously measure whether AI systems remain safe and compliant once deployed. His work bridges the technical rigor of offensive security with the practical demands of governance, risk, and compliance (GRC). Prior to ZioSec, Alex was Senior Security Researcher at ThreatX, a next-generation firewall as a service where he developed multiple patents.