Tech Stack

Description

You will detect, investigate, and disrupt misuse of Anthropic's AI systems for malicious cyber operations, conducting investigations into potential misuse cases, developing novel detection techniques, and building defenses against emerging cyber threats. Your work will protect the ecosystem from sophisticated threat actors leveraging AI for harm.

Requirements

• Proficiency in SQL and Python for data analysis and threat detection
• Experience with large language models and understanding of AI misuse for cyber threats
• Subject matter expertise in abusive user behavior detection (e.g., influence operations, cyber threat intelligence)
• Experience tracking threat actors across surface, deep, and dark web environments
• Strong project management skills and ability to build processes from scratch

Responsibilities

• Detect and investigate misuse of AI systems for cyber operations
• Develop abuse signals and tracking strategies for sophisticated threat actors
• Create actionable intelligence reports on new attack vectors and threat actor TTPs
• Conduct cross-platform threat analysis using open-source, dark web, and internal data
• Build relationships with external threat intelligence partners and government stakeholders