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.
As a Safeguards Analyst focusing on human exploitation and abuse, you will be responsible for building and executing enforcement workflows that detect and mitigate the use of our products to facilitate human trafficking, sextortion, image-based sexual abuse, bullying, and harassment. As a member of the user well-being team, your initial focus will be on standing up detection, review, and escalation workflows for this domain — from tuning classifiers and curating evaluation datasets through to managing external partnerships and real-world harm escalation pathways. This position may later expand to include broader areas of user well-being enforcement. Safety is core to our mission, and you'll help shape policy enforcement so that our users can interact with and build on top of our products across all surfaces in a harmless, helpful, and honest way.
In this position, you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. There is also an on-call responsibility across the Policy and Enforcement teams.
Design and architect automated enforcement systems and review workflows for human exploitation and abuse, ensuring they scale effectively while maintaining high accuracy
Partner with Product, Engineering, and Data Science teams to build and tune detection signals for human trafficking, sextortion, and image-based sexual abuse, and to develop custom mitigations for these sensitive policy areas
Curate policy violation examples, maintain golden evaluation datasets, and track enforcement actions across both consumer and API surfaces
Conduct deep-dive investigations into suspected exploitation activity — using SQL and other data analysis tools to surface threat patterns and bad-actor behavior in large datasets — then produce clear, well-sourced intelligence reports that inform detection strategy and surface policy gaps to the Safeguards policy design team
Study trends internally and in the broa