Research Scientist Engineer Biological Safety
AnthropicVisit Anthropic website
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/23/2026
San Francisco, United States
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and run biological capability evaluations, develop classifier datasets, train and tune classifiers, and analyze production performance. You will build reusable tooling, conduct red-teaming, partner across functions, and communicate biological safety findings.
Requirements
- Python
- Scientific programming
- Data analysis
- Machine learning
- Modern biology
- Quantitative experimentation
- Biosecurity
- Dual-use research
- Tooling
Responsibilities
- Design, build, and run biological capability evaluations
- Develop training and evaluation datasets for safety classifiers
- Train, tune, and iterate on safety classifiers
- Build repeatable evaluation and classifier-development tooling
- Analyze production classifier and evaluation performance
- Design and run red-teaming and stress-testing
- Partner across Research, Product, and Policy teams
- Contribute to external communications
- Track developments in biology, machine learning, and biosecurity
Benefits
- Equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours