ML/Research Engineer, Safeguards

• Develop classifiers to detect misuse and anomalous behavior at scale, including synthetic data pipelines and methods to automatically source representative evaluations
• Build systems to monitor for harms that span multiple exchanges, such as coordinated cyber attacks and influence operations, and develop new methods for aggregating and analyzing signals across contexts
• Evaluate and improve the safety of agentic products by developing threat models, test environments for agentic risks, and mitigations for prompt injection attacks
• Conduct research on automated red-teaming, adversarial robustness, and other research that helps test for or find misuse

This role helps detect and mitigate misuse of AI systems, building safeguards that identify harmful use and develop defenses to keep products safe as capabilities advance, directly feeding into Anthropic's Responsible Scaling Policy commitments.

• 4+ years of experience in ML engineering, research engineering, or applied research in academia or industry
• Proficiency in Python and experience building ML systems
• Comfort working across the research-to-deployment pipeline, from exploratory experiments to production systems
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders

• Competitive compensation: $350,000–$500,000 USD annual salary
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space for collaboration

Anthropic is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Anthropic that we think may be high impact. We do not necessarily recommend working at other positions at Anthropic. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.