Content Adversarial Analyst, Red Team

Trust and Safety team members are tasked with identifying and taking on the biggest problems that challenge the safety and integrity of our products. They use technical know-how, excellent problem-solving skills, user insights, and proactive communication to protect users and our partners from abuse across Google products like Search, Maps, Gmail, and Google Ads. On this team, you're a big-picture thinker and strategic team-player with a passion for doing what’s right. You work globally and cross-functionally with Google engineers and product managers to identify and fight abuse and fraud cases at Google speed - with urgency. And you take pride in knowing that every day you are working hard to promote trust in Google and ensuring the highest levels of user safety.

The Content Adversarial Red Team (CART) in Trust and Safety is a new team that conducts unstructured adversarial testing of Google's premier Generative AI products to uncover new and emerging content risks that are not identified in structured evaluations. CART works alongside product, policy, and enforcement teams to help build the safest possible experiences for Google users.

At Google we work hard to earn our users’ trust every day. Trust & Safety is Google’s team of abuse fighting and user trust experts working daily to make the internet a safer place. We partner with teams across Google to deliver bold solutions in abuse areas such as malware, spam and account hijacking. A team of Analysts, Policy Specialists, Engineers, and Program Managers, we work to reduce risk and fight abuse across all of Google’s products, protecting our users, advertisers, and publishers across the globe in over 40 languages.

• Own and lead red teaming projects to uncover emerging and unknown content safety risks across Google’s core Generative AI products. Focus on this function, which involves, developing and executing innovative red teaming strategies and design targeted, end-to-end testing for specific product scopes.
• Partner with product managers, engineers, researchers, and trust and safety stakeholders to understand product functionality, potential vulnerabilities, and co-develop mitigations.
• Review raw attack results and conduct in-depth qualitative analysis of complex edge cases, translating raw vulnerability data into clear, actionable insights and risks.
• Contribute directly to the development and execution of CART programs to advance AI safety methodologies and operational excellence which include support, development and execution of designated CART programs.
• Evaluate existing project methodologies, identify procedural gaps, refine testing playbooks and Standard Operating Procedures (SOPs) to scale CART’s impact.

Minimum qualifications:

• Bachelor's degree or equivalent practical experience.
• 4 years of experience in adversarial testing, red teaming, GenAI/AI safety, GenAI/AI ethics or responsibility, or a similar field.

Preferred qualifications:

• Master's degree in a related field (e.g., Computer Science, Information Security, Artificial Intelligence).
• Experience working with Google's products and services, particularly GenAI products.
• Experience working with large datasets and data analysis tools and familiarity with different AI model architectures and their vulnerabilities.
• Proven ability to work independently and as part of a team.
• Excellent problem-solving and critical thinking skills with attention to detail in an ever-changing environment.