Principal, Trust and Safety, GenAI, Agentic

Who you are

You have a Bachelor's degree or equivalent practical experience, along with a minimum of 10 years of experience in trust and safety at a technology company. Your background includes at least 7 years in trust and safety, intelligence, security analysis, threat or risk management, geopolitical forecasting, or a related field. You possess 1 year of experience with AI safety and security, adversarial testing, or red teaming, and are familiar with common LLM security vulnerabilities such as prompt injection and data exfiltration. You have a proven track record of making business decisions, identifying gaps or business needs, and innovating and scaling solutions. Your analytical skills are complemented by experience in data analytics using statistical analysis and hypothesis testing, and you have a strong understanding of Machine Learning (ML) models performance or working on Large Language Models (LLMs). You are a logical thinker who thrives in a constantly changing environment and can influence cross-functionally with all levels of management. You excel in high-pressure situations and can manage multiple executive stakeholders, influencing safety strategy and operational execution.

What you'll do

In this role, you will utilize your critical thinking and leadership skills to analyze risks and opportunities presented by emerging agentic features and models. You will design a comprehensive safety strategy that balances these risks and opportunities, defining capabilities and testing requirements for safety risks and security needs. You will support the development of testing requirements for key privacy and security-related needs, particularly around prompt injection and other vulnerabilities. Your role will require you to operate with high-level strategy and executional excellence, ensuring that you provide a consolidated view of risks and mitigations across all launch pillars. You will act as a trusted partner in a fast-paced environment, coordinating with various teams to ensure that safety strategies are effectively implemented and communicated.

What we offer

At Google, you will be part of a team that is dedicated to ensuring the safety and security of AI technologies. You will have the opportunity to work on cutting-edge projects that have a significant impact on the future of technology. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds. Join us in shaping the future of AI safety and security.