Back to jobs
Job Description
- Analyze the evolving AI threat landscape, identifying and forecasting future misuse vectors and adversarial techniques, translating these insights into proactive mitigation plans.
- Apply intelligence to stay ready for new adversarial campaigns or actors, taking enforcement actions to identify and defend against novel fraud and abuse on Google's ad products.
- Lead initiatives to implement next-generation safety mitigations, guiding engineering and research teams in building sophisticated technical solutions, from fine-tuning techniques to classifier-based guardrails.
- Partner closely with Engineering teams to improve ad traffic infrastructure, defense systems, and workflows, proactively identifying and helping implement efficiency improvements through advanced machine learning techniques, scaled defenses, and automation.
- Innovate and develop methods to incorporate AI models to improve quality of the manual review operations as well as develop actionable insights to the engineering teams.