Developed the AI Safety Red Teaming Templates Library for the Azure/PyRIT repository, focusing on structured, scenario-based testing of AI safety controls. Leveraging skills in AI safety research, prompt engineering, and security testing, the work introduced a modular set of YAML templates designed to simulate diverse safety bypass scenarios. This approach established a scalable foundation for repeatable red-teaming exercises, enabling teams to assess risk and align with governance requirements. The integration of the Jailbreak Template Collection streamlined red-teaming workflows, while comprehensive documentation and usage guidelines supported adoption across safety and security teams, facilitating safer and more efficient evaluation of AI systems.