Safeguards Enforcement Analyst, Bio Harms

Anthropic is hiring a Safeguards Enforcement Analyst specializing in Bio Harms for our San Francisco, New York City, Washington DC, and remote-friendly US offices. This full-time position sits at the heart of our AI safety mission, where you'll review model interactions to identify and prevent potential misuse related to biological and CBRNE threats.

Role Overview

Anthropic's commitment to building reliable and beneficial AI systems depends on preventing harmful applications of our technology. In this role, you'll be the gatekeeper against biological misuse—analyzing patterns in how people interact with our AI to spot credible threats and enforce our usage standards. You'll combine deep technical knowledge of biology with platform enforcement expertise, making nuanced judgments about what constitutes legitimate research versus what represents genuine biosecurity risk. Your work directly protects communities and critical infrastructure by keeping our systems from being weaponized. Note: This position involves exposure to explicit content, including material that may be sexual, violent, or psychologically disturbing.

What You'll Do

• Review and assess actual user interactions with AI systems to identify violations related to biological, chemical, radiological, or nuclear threats
• Lead the development and continuous refinement of monitoring systems and workflows specific to biosecurity risks
• Investigate suspected policy violations with rigor, collecting evidence and documenting findings to support enforcement decisions
• Identify emerging threat patterns and anomalies in platform activity that signal new risk vectors requiring policy adaptation or response
• Architect and scale automated detection and review systems that maintain accuracy while handling technically complex content
• Collaborate with Engineering and Data Science to enhance threat detection algorithms and enforcement infrastructure
• Work with Policy and Threat Intelligence teams to refine risk frameworks and identify enforcement blind spots
• Manage escalations and handle time-sensitive situations involving potential bio-related policy breaches
• Participate in on-call rotations shared across Policy and Enforcement teams

Requirements

• Bachelor's degree in a biological science (microbiology, molecular biology, biochemistry, public health, or related field) or equivalent professional biosecurity experience
• Demonstrated experience in trust and safety, content moderation, or policy enforcement at scale—ideally with generative AI platforms
• Proficiency using AI tools for workflow automation, metrics dashboards, and continuous process improvement
• Strong analytical skills with the ability to navigate ambiguous situations and make sound decisions under pressure
• Self-directed mindset: you identify trends proactively, dig into problems, and implement solutions independently
• Excellent written communication with the ability to explain complex biological concepts to both technical and non-technical audiences

Working at Anthropic

Anthropic is a public benefit corporation headquartered in San Francisco, pioneering AI safety research and responsible development. We believe in rigorous science, collaborative teamwork, and diverse perspectives on AI's biggest challenges. We offer competitive compensation, optional equity matching, generous parental and vacation leave, flexible scheduling, and thoughtfully designed office spaces. We sponsor visas where feasible and encourage candidates from underrepresented communities to apply—representation matters in AI. Candidates should expect to spend at least 25% of their time in one of our offices.

Ready to Apply?

To apply, complete your application directly on this page, or you'll be redirected to the employer's application platform to finish submitting there.