Policy Design Manager, Age-Appropriate Design

Details

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. The team includes researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

This role focuses on developing usage policies, clarifying enforcement guidelines, and advising on safety interventions for Anthropic's products and services with a core emphasis on age-appropriate design and experiences. Key focus areas include child safety, age assurance, content classification, and adult sexual content. The role involves defining best practices for developers building on Claude, designing age-assurance policies to protect minors, establishing boundaries for adult content, and advising on opportunities for age-appropriate helpfulness.

Important: In this position you may be exposed to explicit content spanning sexual, violent, or psychologically disturbing material.

Responsibilities

• Serve as an internal subject matter expert leveraging deep expertise in child safety, adult content, youth development, and age-appropriate design to:
  • Draft new policies governing responsible use of models for emerging capabilities and use cases
  • Design evaluation frameworks for testing model performance in areas of expertise
• Conduct regular reviews and testing of existing policies to identify and address gaps and ambiguities
• Review flagged content to drive enforcement and policy improvements
• Update usage policies based on feedback from external experts, enforcement teams, and edge case reviews
• Collaborate with safeguards product teams to identify and mitigate concerns and design appropriate interventions across age groups
• Advise on age assurance approaches and content classification frameworks in partnership with Enforcement, Product, Engineering, and Legal teams
• Educate and align internal stakeholders around policies and safety approaches in your focus areas
• Track AI policy norms, regulatory requirements (e.g., age-appropriate design codes), and industry standards to inform policy decisions

Requirements

• Experience as a researcher, subject matter expert, or trust & safety professional in one or more of: child safety, youth online safety, age assurance, developmental science, content classification and rating systems, or adult content policy
• Preferred: advanced degree in developmental psychology, child development, education, or a related field
• Experience drafting or updating product and/or user policies and bridging technical and policy discussions
• Experience designing or implementing age-appropriate experiences, age assurance mechanisms, or content classification/labeling systems
• Experience working with generative AI products, including writing effective prompts for policy evaluations and classifier development
• Experience aligning product policy decisions across Product, Engineering, Public Policy, and Legal teams
• Understanding of challenges in developing and implementing product policies at scale, including content moderation
• Ability to use data and research to inform policy recommendations and to navigate/prioritize work amid ambiguity

Compensation

• Annual Salary: $245,000 - $285,000 USD

Logistics

• Locations: San Francisco, CA; New York City, NY; Washington, DC
• Education: Minimum Bachelor’s degree in a related field or equivalent experience
• Location-based hybrid policy: staff expected to be in one of Anthropic’s offices at least 25% of the time (some roles may require more)
• Visa sponsorship: Anthropic states they do sponsor visas and retain an immigration lawyer to assist when they make an offer

Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space for collaboration

How we work

Anthropic emphasizes large-scale, cohesive research efforts, collaboration, and communication. The team values impact and publishes research in areas including interpretability, scaling laws, learning from human preferences, and AI safety.