Threat Investigator, Trust & Safety

About the role

As a Threat Investigator, you will be conducting investigations around adversarial actors, identifying vulnerabilities, and developing novel detection techniques to identify and mitigate abuse of our products and services. This role requires conducting thorough investigations, creating and implementing processes, tools, and strategies to proactively detect adversarial actors, managing sensitive incidents, and working cross-functionally to enhance our defenses against emerging risks in the rapidly evolving landscape of AI technology.

Your work will be essential in maintaining Anthropic's commitment to safe and beneficial AI as we continue to expand our product capabilities.

IMPORTANT CONTEXT ON THIS ROLE: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. This role may require responding to escalations during weekends and holidays.

Responsibilities:

• Analyze the deployment of our products and services to identify how these systems are being misused or abused, with a particular focus on influence operations
• Develop abuse signals and tracking strategies to proactively detect adversarial actors
• Study trends internally and in the broader ecosystem to anticipate how systems could be misused or manipulated for harm in the future, generating and publishing reports
• Create actionable intelligence reports on new attack vectors, vulnerabilities, and threat actor TTPs targeting LLM systems
• Utilize the results of deep dive investigations to implement systematic changes to our safety approach to mitigate harm
• Keep abreast of the latest industry risks, vulnerabilities, and issues related to the use of language models and generative AI; identify opportunities for improvement to our policies, controls, and enforcement mechanisms
• Forecast how abuse actors will leverage new advances in AI technology and inform safety by design strategies
• Build and maintain relationships with external threat intelligence partners and information sharing communities
• Work with cross-functional team members to build out our threat intelligence program, establishing processes, tools, and best practices

You may be a good fit if you:

• Have experience in technical analysis and investigations, including skills in SQL and Python
• Have experience with large language models and a deep understanding of AI technology
• Have subject matter expertise in abusive user behavior detection, for example influence operations, coordinated inauthentic behavior patterns, and/or cyber threat intelligence 
• Can derive insights from large amounts of data to make key decisions and recommendations
• Have experience conducting threat actor profiling and utilizing threat intelligence frameworks 
• Have strong project management skills and the ability to build processes from the ground up
• Possess excellent communication skills to collaborate with cross-functional teams