Apply on Employer Site

Anthropic · 5 hours ago

Technical Scaled Abuse Threat Investigator

San Francisco, CA | New York City, NY

Full-time

Hybrid

Mid, Senior Level

$230K/yr - $290K/yr

Anthropic is a public benefit corporation dedicated to creating reliable, interpretable, and steerable AI systems. They are seeking a Technical Scaled Abuse Threat Investigator to join their Threat Intelligence team, responsible for detecting and investigating large-scale misuse of AI systems, as well as developing strategies to combat adversarial activities.

Artificial Intelligence (AI)Foundational AIGenerative AIInformation TechnologyMachine Learning

No H1B

Security Clearance Required

U.S. Citizen Only

Responsibilities

Detect and investigate large-scale abuse patterns including model distillation, unauthorized API access, account farming, fraud schemes, and scam operations

Develop abuse signals and tracking strategies to proactively identify scaled adversarial activity and coordinated abuse networks

Conduct technical investigations using SQL, Python, and data science methodologies to analyze large datasets and uncover sophisticated abuse patterns

Create actionable intelligence reports on new attack vectors, vulnerabilities, and threat actor TTPs targeting AI systems at scale

Utilize investigation findings to implement systematic improvements to our safety approach and mitigate harm

Study trends internally and in the broader ecosystem to anticipate how AI systems could be exploited, generating and publishing reports

Build and maintain relationships with external threat intelligence partners and information sharing communities

Work cross-functionally to build out our threat intelligence program, establishing processes, tools, and best practices

Forecast how abuse actors will leverage advances in AI technology and inform safety-by-design strategies

Qualification

SQLPythonData scienceLarge language modelsAbusive user behavior detectionThreat actor profilingProject managementFluency in MandarinFluency in RussianCommunication skills

Required

Strong proficiency in SQL and Python with a data science background

Experience with large language models and understanding of how AI technology could be exploited at scale

Subject matter expertise in abusive user behavior detection, fraud patterns, account abuse, or platform integrity

Experience tracking threat actors across surface, deep, and dark web environments

Can derive insights from large datasets to make key decisions and recommendations

Experience with threat actor profiling and utilizing threat intelligence frameworks

Strong project management skills and ability to build processes from the ground up

Excellent communication skills to collaborate with cross-functional teams and present to leadership

At least a Bachelor's degree in a related field or equivalent experience

Preferred

Experience at a major technology platform working on trust and safety, fraud, or abuse investigations

Background in AI safety, machine learning security, or technology abuse investigation

Experience building and scaling threat detection systems or abuse monitoring programs

Experience with financial crime investigation or fraud analytics

Fluency in Mandarin Chinese and/or Russian (speaking, reading, and writing) combined with a nuanced understanding of the geopolitical landscape and cultural context of the respective regions

Active Top Secret security clearance