Safeguards Enforcement Analyst, Conventional Weapons

The posting, as Anthropic wrote it

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 Enforcement Analyst focused on Conventional Weapons, your work spans detecting and mitigating attempts to misuse Anthropic's AI systems to facilitate real-world harm, specifically utilizing conventional weapons and dangerous technology. You will be responsible for building and executing operational workflows to assess model behavior, drive enforcement decisions, and develop evals across a technically demanding range of policy areas.

Important context for this role: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a violent, graphic, hateful, or psychologically disturbing nature.

Key responsibilities

Design and architect automated enforcement systems and review workflows that scale effectively while maintaining high accuracy

Develop and maintain evals that measure model performance on these policy areas, surface regressions, and inform policy and model improvements

Partner with Engineering and Data Science to optimize detection and automated enforcement systems for potential policy violations

Review flagged content to drive enforcement decisions and surface policy gaps, with particular attention to novel or technically sophisticated misuse attempts + emerging tactics

Support the Safeguards policy design team by providing structured feedback on policy gaps and enforcement ambiguities based on real enforcement scenarios

Develop and maintain enforcement guidelines and reviewer documentation that enable accurate, consistent enforcement across a wide range of content

Keep up to date with emerging weapons trends and applications, regulatory changes, and AI policy enforcement best practices, and apply these to inform our workflows and evals

Identify and escalate emerging misuse patterns, novel attack vectors, and signs of coordinated violent activity

Minimum qualifications

Have deep, applied expertise in weapons systems and can translate complex technical evidence to make enforcement decisions

Experience in policy enforcement, threat intelligence, counterterrorism, government, or a closely related field, with direct exposure to harmful content, dangerous technology, or physical harm facilitation

Experience standing up and scaling policy enforcement or content review workflows

Proficiency in SQL and/or other data analysis tools to draw insights from large datasets and monitor enforcement workflow health

Experience identifying emerging risks and threat actors, and communicating findings to a diverse set of stakeholders, such as Product, Policy, Engineering, and Legal teams

[…]
n our team.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

How we're different

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.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.