Job Summary
The Security Engineer is tasked with assessing Cloud AI infrastructures for potential vulnerabilities including jailbreaks and prompt injections. This role also involves the development of anti-abuse detection mechanisms, alongside probing into abuse occurrences and offering security recommendations to engineering teams to fortify AI product integrity.
Responsibilities
- Conduct security assessments on Cloud AI systems to identify vulnerabilities.
- Develop and implement anti-abuse detection systems.
- Investigate incidents of abuse to understand threat patterns.
- Provide security-related guidance and support to engineering teams.
Qualifications
- Bachelor’s degree in a relevant field.
- A minimum of 2 years of experience in security engineering.
- Experience with threat modeling and coding practices.
- Preferred expertise in AI safety and large language models (LLMs).
- Ability to recognize and address security vulnerabilities effectively.
Google provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
