Research Scientist/Engineer, Biological Safety

San Francisco, CA

Posted 9d ago

Job Location

San Francisco, CA

Tech Stack

Remote Work Policy

On-site

Categories

AI Research Engineer

About the job

Anthropic is building reliable, interpretable, and steerable AI systems to be safe and beneficial for users and society. As a Safeguards Biological Safety Research Scientist, you will apply your technical skills to design and develop safety systems that detect harmful AI behaviors and prevent misuse by sophisticated threat actors. This role is at the forefront of defining responsible AI safety in the biological domain, translating complex biosecurity concepts into technical safeguards and balancing AI's potential for life sciences research with preventing misuse.

Responsibilities

  • Design and execute capability evaluations to assess new model capabilities.
  • Collaborate with threat modeling experts to develop training data for safety systems.
  • Train safety systems with ML engineers, optimizing for robustness and low false-positive rates.
  • Analyze safety system performance in production to identify gaps and propose improvements.
  • Develop rigorous stress-testing of safeguards against evolving threats.
  • Partner with Research, Product, and Policy teams to embed biological safety in model development.
  • Contribute to external communications, including model cards, blog posts, and policy documents.
  • Monitor emerging technologies for new risks and mitigation strategies.

Requirements

  • PhD in a life sciences field (e.g., molecular biology, virology, biochemistry) or equivalent professional experience.
  • Extensive experience in scientific computing and data analysis.
  • Proficiency in programming, with Python preferred.
  • Deep expertise in modern biology, including both 'reading' and 'writing' techniques.
  • Familiarity with dual-use research concerns, select agent regulations, and biosecurity frameworks.
  • Strong analytical and writing skills, with the ability to explain complex technical concepts.
  • Passion for learning new skills and adapting to changing technologies.
  • Comfort working in a fast-paced environment with shifting priorities.

Benefits

  • Annual compensation range: $300,000 - $320,000 USD
  • Visa sponsorship available

About Anthropic

Get new AI jobs in your inbox

A weekly digest of the newest AI engineering roles.

© 2026 AI Job Board. All rights reserved.