Executing comprehensive plans to assess the safety and security of Meta's language model, specializing in Vietnamese, focusing on identifying potential weaknesses and vulnerabilities.Collaborating closely with the development team to design and execute probing dialogs, evaluating the model's responses, and providing valuable feedback on both the quality of the model and the probing methodologies used.Identifying and reporting vulnerabilities in Meta's language model, contributing to improvements in its safety and accuracy.Developing and executing probing dialog strategies that exposed areas for model enhancement, leading to increased trust and user satisfaction.Maintaining up-to-date knowledge of AI security best practices, playing a crucial role in safeguarding Meta's language model from potential threats.

Collaborate with the design and development teams to create, develop, and implement user interface designs within the RadicalX platform.Contribute to the improvement and refinement of UI for the AI Dev Manager powered by GPT-4, leveraging the latest trends and techniques in UI design.Conduct user research and usability testing to ensure that our designs meet user needs and enhance the user experience.Assist in the creation of design prototypes, wireframes, and mockups to visualize and communicate design ideas.Present design and receive feedback during the team meeting.

Provided administrative support to faculty and staff in various departments, including scheduling appointments, managing correspondence, and maintaining databases.Designed flyers by using Canva to promote awareness campaigns, and generated evaluation forms.Assisted in the coordination of events, workshops, and meetings.Conducted literature searches and data entry for research projects.

Organizing and maintaining the cleanliness of the workplaceScheduling appointments and fulfilling students’ needsTroubleshooting simple computer errors