Design YAML-based adversarial prompt injection scenarios, test them against frontier models, and validate successful tasks that assess whether AI agents can be manipulated into violating safety policies.
This role focuses on building multimodal understanding systems that enable Descript's AI editing features to reason over visual and audio content, enhancing the editing workflow.
Design, build, and deploy production-grade AI agents that automate complex business workflows, owning agent architecture, knowledge systems, evaluation, and cross-functional delivery across enterprise functions.
Design real-world strategy tasks and evaluation criteria for AI models, drawing on hands-on experience with strategy readouts, market sizing, competitive landscapes, and due diligence work.
Research education, AI, and technology policy across MENA markets, mapping government priorities and stakeholders and turning findings into practical recommendations for institutional adoption and engagement.
