Safeguards Enforcement Analyst, Cyber Harm

As an Enforcement Analyst, you will be responsible for reviewing content and executing enforcement actions across our products and services, with a focus on detecting and mitigating attempts to misuse Anthropic’s AI systems for malicious cyber operations. Your initial focus will center on reviewing flagged activity related to cyberattacks, malware development, and offensive exploitation; however, this position may later expand to include broader areas of enforcement., * Review flagged content and accounts to make accurate, well-documented enforcement decisions in line with our usage policies

• Detect and mitigate potential misuse of AI systems to facilitate cyberattacks, malware creation, exploitation tooling, and related harmful cyber operations
• Triage and escalate novel, ambiguous, or high-severity cases to appropriate stakeholders
• Provide detailed feedback to the Safeguards policy design team on policy gaps surfaced through real enforcement scenarios
• Partner with Engineering and Data Science teams by surfacing detection model errors and quality signals from review to improve precision and recall
• Maintain high accuracy and consistency standards across review queues
• Keep up to date with emerging AI policy enforcement best practices, threat actor tactics, and the evolving cyber threat landscape, using these to inform enforcement decisions

• Experience in cybersecurity, including knowledge of offensive techniques, exploit development, malware analysis, or vulnerability research
• Experience performing content review, abuse investigations, or policy enforcement at volume
• Proficiency in SQL and/or Python for data analysis and threat detection
• Experience identifying emerging risks and communicating findings to a diverse set of stakeholders, such as Product, Policy, Engineering, and Legal teams
• Experience working with generative AI products, including writing effective prompts for content review and enforcement, * Experience in trust & safety, abuse investigations, cybersecurity investigations, or threat intelligence in a technology or AI company
• Experience with large language models and an understanding of how AI technology could be misused for cyber operations
• Experience operating within abuse monitoring programs or enforcement review systems
• Understanding of the challenges involved in implementing product policies at scale, including in the content moderation space
• Experience working with government agencies, regulated environments, or information sharing communities, Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Remote Hybrid work $285,000 - $330,000 a year, Pulled from the full job description Parental leave Flexible schedule

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., We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact - advancing our long-term goals of steerable, trustworthy AI - rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We’re an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.