Research Scientist/Engineer, Biological Safety

The role

You will build safety and oversight mechanisms for models handling biological knowledge. This involves designing capability evaluations, generating training data for safety classifiers, and measuring performance against adversarial pressure.

What you will do

• Design, build, and run capability evaluations to assess new models in the biological domain
• Develop training and evaluation datasets for safety classifiers
• Train, tune, and iterate on safety classifiers with ML engineers
• Build tooling and pipelines for evaluation and classifier development
• Analyze classifier and eval performance against production traffic
• Design and run red-teaming and stress-testing of safeguards
• Partner with Research, Product, and Policy teams to embed biological safety
• Contribute to external communications including model cards, blog posts, and policy documents
• Track developments in biology, ML, and biosecurity

Required qualifications

• Strong proficiency in Python
• Extensive background in scientific programming and data analysis skills
• Excellent grasp of ML fundamentals
• Ability to rapidly adopt ML development practices
• Excellent knowledge of modern biology across measurement and engineering
• Ability to build and maintain your own tooling
• Experience designing quantitative experiments or evaluations
• Strong analytical and writing skills
• Ability to explain technical concepts to non-technical stakeholders
• Familiarity with dual-use research concerns and biosecurity frameworks
• Comfort with ambiguity and shifting priorities
• Bachelor’s degree or an equivalent combination of education, training, and/or experience in a relevant field

Nice to have

• Experience working with large language models, including prompting, fine-tuning, or evaluation
• Experience training or deploying classifiers or other ML systems in production
• Experience developing ML methods for biological systems or biological data
• Familiarity with adversarial robustness, red-teaming, or safety evaluation of ML systems
• At least 8 years of hands-on experience in life sciences
• Experience leading complex technical projects across multiple stakeholder groups

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, though not for every role or candidate

About the company

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