ML/Research Engineer, Safeguards

The role

ML Engineers and Research Engineers will build systems to detect and mitigate misuse of AI systems. This includes developing classifiers, monitoring for harms, and evaluating the safety of agentic products.

What you will do

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

Required qualifications

• 4+ years of experience in ML engineering, research engineering, or applied research, in academia or industry
• Proficiency in Python
• Experience building ML systems
• Comfortable working across the research-to-deployment pipeline
• Strong communication skills
• Bachelor’s degree or an equivalent combination of education, training, and/or experience
• A field relevant to the role as demonstrated through coursework, training, or professional experience

Nice to have

• Language modeling and transformers
• Building classifiers, anomaly detection systems, or behavioral ML
• Adversarial machine learning or red-teaming
• Interpretability or probes
• Reinforcement learning
• High-performance, large-scale ML systems

Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space

Before you apply

• We do sponsor visas

About the company

Anthropic is a public benefit corporation headquartered in San Francisco. Its mission is to create reliable, interpretable, and steerable AI systems.