Join Google's Trust and Safety team as a Content Adversarial Analyst, Red Team. This role is pivotal in ensuring the safety and integrity of our cutting-edge Generative AI products.

You'll be at the forefront of identifying and mitigating emerging content safety risks through unstructured adversarial testing. Your work will directly contribute to building safer and more trustworthy AI experiences for millions of users worldwide.

This is an opportunity to be a key player in a dynamic and innovative environment, working cross-functionally to address complex challenges in AI safety and security.

Lead end-to-end red teaming projects focused on uncovering novel content safety risks and vulnerabilities in Google's Generative AI products.

Develop and implement innovative testing strategies, designing targeted assessments to identify potential issues.

Collaborate closely with product managers, engineers, researchers, and stakeholders to understand product functionalities and potential risks.

Conduct in-depth qualitative analysis of attack results, translating raw data into clear, actionable insights and risk assessments.

Contribute to the ongoing development and execution of program methodologies, refining testing playbooks and Standard Operating Procedures (SOPs) to enhance operational excellence.

A Bachelor's degree or equivalent practical experience is required.

Four years of dedicated experience in adversarial testing, red teaming, GenAI/AI safety, or a related field are essential.

A Master's degree in Computer Science, Information Security, Artificial Intelligence, or a similar discipline is preferred.

Familiarity with Google's products, large datasets, data analysis tools, and diverse AI model architectures is highly beneficial.

Demonstrated ability to work both independently and collaboratively, coupled with excellent problem-solving and critical thinking skills, is expected.