Safeguards Policy Analyst, Fraud & Scams

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the Role As a Safeguards Policy Analyst focused on Fraud and Scams, you will be responsible for designing, building, and executing enforcement workflows that detect and mitigate fraud and scam-related harms on Anthropic s products. You will serve as the subject matter expert on fraud typologies, scam ecosystems, and the threat actors who perpetrate them — translating that expertise into durable and scalable policies. This role sits within the Integrity and Authenticity (I and A) team, You will function both as a policy owner, and work closely with threat investigative and enforcement teams. You will also develop the guidelines that power classifiers, and will be our point of content cross-functional workstreams. No two days will look the same. strong Important context: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a financial, psychological, or otherwise disturbing nature, including detailed fraud schemes and scam content. Responsibilities: Policy Design and Ownership Draft, maintain, and iterate on Fraud and Scams policies governing Anthropic s products and APIs, with clarity for both model enforcement and human reviewers Conduct regular structured policy reviews to identify gaps, ambiguities, and coverage failures, and lead the process to close them Develop detailed threat models for fraud and scam vectors — including social engineering, financial fraud, impersonation scams, phishing, and AI-enabled fraud — and translate these into enforceable policy language Stay current on the fraud and scam landscape, including emerging typologies, regulatory shifts, and threat actor tactics, techniques, and procedures (TTPs) Enforcement Strategy and Operations Design and architect automated enforcement systems and human review workflows that scale effectively while maintaining high precision and recall Review flagged content to drive enforcement decisions and surface policy improvements grounded in real-world cases Define and manage precision/recall tradeoffs in enforcement, working with data science teams to continuously tune classifiers and detection