Content Adversarial Red Team Analyst
Summary
A senior analyst on Google's Trust & Safety team who designs and executes red teaming strategies to probe Google and GenAI products for abuse and vulnerabilities, partners cross-functionally with engineers, PMs, and researchers, and mentors junior analysts while advancing AI safety programs.
- Develop and execute innovative red teaming strategies. Proactively identify emerging threats and design highly targeted testing approaches.
- Partner with product managers, engineers, researchers, and other stakeholders to understand product functionality, potential vulnerabilities, and develop actionable solutions.
- Guide and support the development of junior analysts, sharing knowledge and expertise to build a high-performing team.
- Identify key areas for improvement and develop comprehensive program plans.Evaluate and optimize existing programs, identifying areas for improvement and enhancing their impact.
- Advocate for the importance of AI safety within Google and the wider industry and knowledge of AI landscape and tools.
Minimum qualifications:
- Bachelor's degree or equivalent practical experience.
- 7 years of experience in data analytics, Trust and Safety, policy, cybersecurity, or related fields.
Preferred qualifications:
- Master's degree in Computer Science, Information Security, Artificial Intelligence, or a related field.
- Experience working with Google's products and services, particularly GenAI products.
- Experience working with large datasets and data analysis tools.
- Familiarity with different AI model architectures and their vulnerabilities.
- Proficiency in multiple languages, especially those relevant to Google's global user base.
- Excellent problem-solving and critical thinking skills with attention to detail in an ever-changing environment.