About the job
The Trust & Safety (T&S) GenAI & Emerging Product team's mission is to empower the development of GenAI models and applications. We do this by building a world-class safety, testing, and risk management system that ensures GenAI innovations are launched responsibly. The AI Content Red Team sits within the T&S GenAI and Emerging Products pillar. The team is responsible for conducting unstructured adversarial testing of generative AI products and models to uncover emerging risks, alongside our structured evaluations.
Responsibilities
- Lead the global AI Content Red Team, including team strategy, hiring, people management, and capability building.
- Design and oversee end-to-end adversarial testing programs for GenAI products.
- Establish testing methodologies to simulate adversarial behaviors, edge cases, and real-world abuse scenarios.
- Drive discovery of emerging content risks, abuse patterns, and safety strategy failure modes across text, image, video, audio, agentic modalities.
- Develop mechanisms to track themes, trends, and escalate high-severity findings that may impact user safety, compliance, or brand risk. Ensure testing outputs are actionable and well-documented.
- Partner with Product, Policy, and business teams to ensure red-teaming insights directly inform product design, safety mitigations, and policy frameworks.
- Represent team in cross-functional forums, and serve as a key risk voice in product readiness discussions.
Qualifications
Minimum
- Minimum 5 years in Trust & Safety, cybersecurity, risk/adversarial testing, or related fields.
- Minimum 5 years in a lead role (team lead, program lead, or equivalent).
- Direct experience in adversarial testing / red-teaming / vulnerability discovery, particularly of Generative AI.
- Strong understanding of LLM behavior, model failure modes, and safety risks.
- Experience building or scaling safety, QA, or risk-focused teams.
- Strong ability to influence product and launch decisions.
- Proven cross-functional leadership with Product, Engineering, Policy, Risk, and business teams.
Preferred
- Experience working with agentic AI tools to scale your impact, including building/operating AI tools to make processes efficient and effective.