Principal AI Security Researcher

The Principal AI Security Researcher will lead and scale multidisciplinary teams focused on AI red teaming, adversarial testing, and AI security research. They will design and execute sophisticated attacks against large language models, generative AI applications, and agentic AI systems, and build automated red‑teaming engines and guardrails. The role involves shaping AI security strategy, collaborating with product and engineering, and driving the development of enterprise‑ready AI security solutions.