AI CBRN-E Threat Investigator — Threat Intelligence

Anthropic Limited; San Francisco, New York, Washington (CA, NY, District of Columbia); Sur place; USD 120 000 - 190 000; Plein temps

Résumé du poste

Anthropic is seeking a Technical CBRN-E Threat Investigator to join our Threat Intelligence team in San Francisco, NY, or DC. You will detect and investigate attempts to misuse Anthropic's AI systems for CBRN-E threats, develop detection capabilities, and build defenses against threat actors leveraging AI for harm.

The role requires hands-on data analysis, cross-platform threat assessment, and collaboration with policy and enforcement teams. Weekend/holiday escalations may be required.

Qualifications

• Experience in intelligence investigations or security research.
• Ability to analyze large datasets and detect misuse patterns.
• Knowledge of CBRN-E security domain is a plus.

Responsabilités

• Detect and investigate attempts to misuse Anthropic's AI systems for developing, enhancing, or disseminating CBRN-E weapons, pathogens, toxins, or other threats to harm people, critical infrastructure, or the environment.
• Conduct technical investigations using SQL, Python, and other tools to analyze large datasets, trace user behavior patterns, and uncover sophisticated CBRN-E threat actors.
• Develop CBRN-E-specific detection capabilities, including abuse signals, tracking strategies, and detection methodologies tailored to dual-use research concerns.
• Create actionable intelligence reports on CBRN-E attack vectors, vulnerabilities, and threat actor TTPs leveraging AI systems.
• Conduct cross-platform threat analysis grounded in real threat actor behavior, open-source research, and publicly reported programs.
• Collaborate with policy and enforcement teams to make informed decisions about user violations and ensure appropriate mitigation actions.
• Engage with external stakeholders including government agencies, regulatory bodies, scientific organizations, and biosecurity/chemical security research communities.
• Inform safety-by-design strategies by forecasting how threat actors may leverage advances in AI technology for CBRN-E purposes.

Connaissances

SQL

Python

Threat intelligence

Data analysis

Description du poste

Anthropic is seeking a Technical CBRN-E Threat Investigator to join our Threat Intelligence team in San Francisco, NY, or DC. You will detect and investigate attempts to misuse Anthropic's AI systems for CBRN-E threats, develop detection capabilities, and build defenses against threat actors leveraging AI for harm.

The role requires hands-on data analysis, cross-platform threat assessment, and collaboration with policy and enforcement teams. Weekend/holiday escalations may be required.