Acting as a trusted , you collaborate with legal, compliance, and data protection teams to shape governance and regulatory alignment for AI security. * Leading the design of a multi-layered defense strategy, you protect against jailbreaks, prompt injection, data exfiltration, and tool misuse through advanced input/output scanners, safety filters, and autonomous agents. * You drive operational excellence: define KPIs, implement canary rollouts, optimize cost/performance, scale to additional data sources, and ensure 24/7 reliability. * Mentoring and guiding an agile team of engineers and data scientists, you foster 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.
mehr