Safeguards ML Engineer: Detect & Defend AI Misuse

Anthropic Limited; New York (NY); Hybrid; USD 350,000 - 500,000; Full time

Job summary

Anthropic is seeking ML Engineers and Research Engineers to detect and mitigate misuse of our AI systems. You will build classifiers, monitor for harms, and develop defenses that keep products safe as capabilities advance.

The role sits within the Safeguards ML team, contributing to responsible scaling policies and user wellbeing. You will work across research-to-deployment pipelines, from exploratory experiments to production systems, addressing a broad range of misuse scenarios and

Qualifications

• Have 4+ years of experience in ML engineering, research engineering, or applied research.
• Have proficiency in Python and experience building ML systems.
• Are comfortable working across the research-to-deployment pipeline, from exploratory experiments to production systems.
• Are worried about misuse risks of AI systems, and want to work to mitigate them.
• Have strong communication skills and ability to explain complex technical concepts to non-technical stakeholders.

Responsibilities

• Develop classifiers to detect misuse and anomalous behavior at scale.
• Build systems to monitor for harms that span multiple exchanges, such as coordinated cyber attacks and influence operations.
• Evaluate and improve the safety of agentic products—developing both threat models and environments to test for agentic risks, and developing and deploying mitigations for prompt injection attacks.
• Conduct research on automated red-teaming, adversarial robustness, and other research that helps test for or find misuse.

Skills

ML engineering

Python

Deployment pipelines

Misuse mitigation

Communication

Job description

Anthropic is seeking ML Engineers and Research Engineers to detect and mitigate misuse of our AI systems. You will build classifiers, monitor for harms, and develop defenses that keep products safe as capabilities advance.

The role sits within the Safeguards ML team, contributing to responsible scaling policies and user wellbeing. You will work across research-to-deployment pipelines, from exploratory experiments to production systems, addressing a broad range of misuse scenarios and