Research Scientist/Engineer - AI Safety (Biosecurity)

Anthropic is seeking a Research Scientist or Research Engineer to join their team focused on researching and mitigating extreme risks from future AI models. The role involves leading research projects to baseline current models and test potential harm from future frontier capabilities, with a focus on biosecurity risks.

Key responsibilities include:

• Designing and running scientific experiments on large language models
• Developing novel evaluations for biosecurity implications
• Synthesizing research to establish thresholds of concern for AI capabilities
• Improving internal technical infrastructure and tools
• Collaborating with cross-functional partners

The ideal candidate will have an advanced degree in biological sciences or professional experience in biology research, combined with familiarity in machine learning or software engineering. For the Research Engineer track, professional experience in software engineering or machine learning with an interest in biosecurity is required.

Anthropic offers a competitive salary range of $280,000 - $315,000 USD, along with benefits such as visa sponsorship, flexible working hours, and a collaborative office space in San Francisco. The company values diversity and encourages applications from underrepresented groups.

Anthropic is committed to big science AI research, working as a cohesive team on large-scale efforts to advance steerable, trustworthy AI. They prioritize impact and view AI research as an empirical science, valuing communication skills and collaboration highly.