AI Threat Intelligence Investigator

Anthropic; United States; Hybrid; USD 230,000 - 290,000; Full time

Job summary

Anthropic is seeking a Technical Cyber Threat Investigator to join our Threat Intelligence team. You will detect, investigate, and disrupt the misuse of Anthropic's AI systems for malicious cyber operations.

Working at the intersection of AI safety and cybersecurity, you will develop detection techniques, build defenses, and generate intelligence reports on evolving threats to LLM systems.

Qualifications

• 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 and threat intelligence frameworks.

Responsibilities

• Detect and investigate attempts to misuse Anthropic’s AI systems for cyber operations.
• Develop abuse signals and tracking strategies to detect threat actors across our platform.
• Create actionable intelligence reports on new attack vectors, vulnerabilities, and threat actor TTPs targeting LLM systems.
• Conduct cross-platform threat analysis using open-source research, dark web monitoring, and internal data.
• Utilize findings to improve safety approaches and mitigate harm at scale.
• Study trends internally and in the broader ecosystem to publish reports.

Skills

SQL

Python

Threat detection

Threat intelligence

MITRE ATT&CK

Education

Bachelor’s degree or equivalent

Tools

MITRE ATT&CK

Job description

Anthropic is seeking a Technical Cyber Threat Investigator to join our Threat Intelligence team. You will detect, investigate, and disrupt the misuse of Anthropic's AI systems for malicious cyber operations.

Working at the intersection of AI safety and cybersecurity, you will develop detection techniques, build defenses, and generate intelligence reports on evolving threats to LLM systems.