ML/Research Engineer, Safeguards

Core responsibilities:

• Develop classifiers to detect misuse and anomalous behavior at scale, including synthetic data pipelines and methods for sourcing evaluations
• Build systems to monitor for harms spanning multiple exchanges, such as coordinated cyber attacks and influence operations
• Evaluate and improve the safety of agentic products by developing threat models, test environments, and mitigations for prompt injection attacks
• Conduct research on automated red-teaming, adversarial robustness, and other methods to test for or find misuse

This role helps detect and mitigate misuse of AI systems, protecting user wellbeing and ensuring models behave appropriately across contexts, directly supporting Anthropic's Responsible Scaling Policy commitments to create safe and beneficial AI.

Required qualifications:

• 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 and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space for collaboration. The annual salary range is $350,000–$500,000 USD.

Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society, with a team of researchers, engineers, policy experts, and business leaders working together on high-impact AI research.