Job Summary
This role focuses on the design and execution of sophisticated methodologies aimed at assessing the safety of AI systems. This includes the implementation of red teaming and adversarial testing techniques. The position will require collaboration with various stakeholders to convert security insights into practical enhancements for the robustness of AI models.
Responsibilities
- Develop and implement innovative strategies for evaluating AI system safety.
- Conduct red teaming and adversarial testing of AI models.
- Work alongside stakeholders to interpret security findings and suggest actionable improvements.
Qualifications
- A minimum of 2 years of experience in adversarial machine learning or evaluating AI safety.
- An advanced degree in computer science, cybersecurity, or a related discipline is preferred.
