Biological Safety Research Scientist
$300k/y-$320k/y
Anthropica day ago
Highlight
HybridFull-timeMid
Summary
Anthropic is seeking a Biological Safety Research Scientist to join their team in New York, NY. The role involves designing and developing safety systems for AI to detect harmful behaviors and prevent misuse.
About the Role
As a Safeguards Biological Safety Research Scientist, you will be responsible for designing capability evaluations, collaborating with threat modeling experts, analyzing safety system performance, developing stress-testing protocols, and ensuring biological safety is integrated throughout the model development lifecycle. You will also contribute to external communications and monitor emerging technologies for potential risks.
About You
Required:
- PhD in molecular biology, virology, microbiology, biochemistry, systems or computational biology, or a related life sciences field, OR equivalent professional experience.
- Extensive experience in scientific computing and data analysis, with proficiency in programming (Python preferred).
- Deep expertise in modern biology techniques including high-throughput measurement and gene synthesis.
- Familiarity with dual-use research concerns and biosecurity frameworks.
- Strong analytical and writing skills, with the ability to explain complex technical concepts to non-technical stakeholders.
Preferred:
- Background in AI/ML systems, particularly experience with large language models.
- Experience in developing ML for biological systems.
- Extensive experience in complex projects with multiple stakeholders.
Benefits
- Competitive compensation with an annual salary range of $300k–$320k.
- Generous vacation and parental leave.
- Flexible working hours.
- Optional equity donation matching.
Anthropic
We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.
New York, NY