You design and lead a multi-layered defense strategy against jailbreaks, prompt injection, data exfiltration, and tool misuse through advanced input/output scanners, safety filters, and autonomous agents. * You mentor and guide an of and , fostering best practices in architecture, security, and platform engineering. * Deep expertise in LLM and agent security: advanced protection against jailbreaks, prompt and indirect injection, input/output scanners, policy engines, and moderation strategies. * Strong engineering background with architectural decision-making: Python, C# or TypeScript, REST and event-driven systems, observability practices, and experience with agile methods.
mehr