Enforce Anthropic's usage policy against radiological and nuclear harms by investigating model interactions, owning monitoring workflows, and partnering with Policy, Threat Intelligence, Data Science, and Engineering teams to strengthen safeguards. Requires nuclear-related degree/experience plus Trust & Safety background; involves exposure to disturbing content and on-call duties.
245k – 285k/yr
Hybrid5+ YOEOther
About the role
Key Responsibilities
Enforce Usage Policies with a specific focus on detecting and mitigating potential radiological and nuclear risks.
Own enforcement monitoring workflows for the radiological and nuclear harm area, improving end-to-end detection, investigation, triage, and escalation processes.
Monitor and analyze platform activity to identify emerging patterns related to radiological and nuclear threats (within the broader CBRNE landscape) that may require policy updates or interventions.
Design and architect automated enforcement systems and review workflows that scale effectively while maintaining high accuracy across a technically complex content surface.
Conduct thorough investigations of potential violations, gathering and documenting evidence to support enforcement decisions.
Proactively surface trends and propose improvements to detection methods and review workflows.
Partner with Engineering and Data Science teams to optimize detection models and automated enforcement systems for policy violations.
Partner with Policy and Threat Intelligence teams to understand potential exploits and contribute to risk-assessment frameworks, and partner with engineers iterating on safety systems.
Provide enforcement-grounded feedback on policy gaps, and handle escalations and time-sensitive situations related to radiological and nuclear policy violations.
Minimum Qualifications
Undergraduate degree in a physics- or nuclear-related field (e.g., physics, nuclear engineering, health physics, radiochemistry) and/or relevant professional experience in a related field.
Experience in Trust & Safety, content moderation, or policy enforcement at platform scale, including working with generative AI tools to refine and optimize content review and enforcement workflows.
Experience utilizing AI tools to develop data dashboards for metrics collection in support of continuous improvement efforts.
Ability to analyze complex, ambiguous situations and make well-reasoned, defensible decisions under time pressure.
Proactive and self-directed: spot trends, dig in, and ship improvements on your own initiative.
Maintain emotional resilience when working with potentially disturbing content over time.
Communicate clearly in writing and translate technical radiological or nuclear concepts for diverse audiences, including both technical and non-technical stakeholders.
Preferred Qualifications
Subject matter expertise in radiological and nuclear defense, security, WMD/CBRNE non-proliferation, or threat-intelligence.
Understand where real-world radiological and nuclear risk actually lies — adversary intent, special-nuclear-material and source acquisition, enrichment, and device pathways.
Proficiency in SQL and/or other data analysis tools to draw insights from large datasets and monitor enforcement workflow health.
Familiarity with IAEA safeguards, the NPT, special-nuclear-material and radioactive-source security, NNSA guidelines, and proliferation-pathway analysis.
Safeguards Enforcement Analyst owning the end-to-end fraud and scams program at Anthropic: define policy taxonomy, build detection-to-enforcement pipelines, investigate organized abuse rings, create durable controls and contractor playbooks, and quantify losses to drive strategy. Requires deep payment-fraud and program-building experience.
245k – 285k/yr
Hybrid5+ YOEOther
Safeguards Enforcement Analyst, Ban Evasion & Recidivism
AnthropicSan Francisco, CA +2
Investigate and mitigate ban evasion and recidivism for high-stakes safety enforcement (including child-safety bans) at Anthropic. Build detection frameworks, link accounts across identities, operationalize controls, and partner with engineering/data science teams using SQL and fraud signals.
Enforce Anthropic's usage policies by detecting and mitigating chemical and explosives misuse of AI models. Investigate platform interactions, own monitoring workflows, design automated enforcement systems, and partner with Policy, Threat Intelligence, Data Science, and Engineering teams. Requires chemistry background plus Trust & Safety experience.
245k – 285k/yr
HybridOther
Safeguards Enforcement Analyst, Bio Harms
AnthropicSan Francisco, CA +2
Enforce Anthropic's Usage Policy against biological and CBRNE harms by investigating model interactions, owning bio-harms monitoring workflows, and partnering with Policy, Threat Intelligence, Data Science, and Engineering teams to improve detection and safeguards. Requires bio-related degree/experience plus Trust & Safety background.
245k – 285k/yr
Hybrid5+ YOEOther
Safeguards Enforcement Analyst, Child Safety
AnthropicSan Francisco, CA +2
Manage and scale child safety content review workflows for detecting and responding to CSAM/CSEM generated by Anthropic's AI products. Requires trust & safety operations experience with child protection, SQL proficiency, and cross-functional collaboration with Engineering, Policy, and Legal teams.