Technical CBRN E Threat Investigator

AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.

Series F+Recently funded0 current maintainers0 active leads
San Francisco, United States
About Anthropic

Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.

View jobs by Anthropic

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will detect, investigate, and help disrupt attempts to misuse AI systems for chemical, biological, radiological, nuclear, and explosive threats. You will analyze large datasets and user behavior, develop detection methods, produce actionable threat intelligence, and work with policy, enforcement, external stakeholders, and safety teams to mitigate risks.

Requirements

  • Deep expertise in biosecurity, chemical defense, biological weapons non-proliferation, dual-use research, synthetic biology, or related CBRN-E domains
  • SQL proficiency
  • Python proficiency
  • Threat actor profiling experience
  • Threat intelligence framework knowledge
  • Hands-on experience with large language models and AI misuse risks
  • Stakeholder management across researchers, policy experts, legal teams, and external partners
  • Ability to present analysis to technical and non-technical audiences

Responsibilities

  • Detect and investigate attempts to misuse AI systems for CBRN-E threats
  • Analyze large datasets and user behavior patterns using SQL, Python, and other tools
  • Develop CBRN-E-specific abuse signals, tracking strategies, and detection methodologies
  • Create actionable intelligence reports on attack vectors, vulnerabilities, and threat actor TTPs
  • Conduct cross-platform threat analysis using open-source research and public reporting
  • Collaborate with policy and enforcement teams on user violations and mitigation actions
  • Engage government agencies, regulators, scientific organizations, and security research communities
  • Inform safety-by-design strategies by forecasting AI-enabled CBRN-E misuse

Benefits

  • Optional equity donation matching
  • Generous vacation
  • Parental leave
  • Flexible working hours
Technical CBRN E Threat Investigator at Anthropic | JobStash