Remote
Anthropic seeks a cybersecurity expert to lead efforts against AI misuse in the cyber domain, designing safety systems and developing policies. The role involves threat modeling, policy creation, and collaboration with various teams to ensure responsible AI development. The position requires translating cybersecurity knowledge into actionable safety requirements.
Cybersecurity, Threat modeling, Policy development, AI/ML systems, Vulnerability research, Exploit development, Network security, Malware analysis, Penetration testing, Data analysis, Python programming
Our total compensation package for full-time employees includes equity and benefits.