Research Scientist/Engineer, Biological Safety

Anthropic is looking for research engineers to build the safety and oversight mechanisms that govern how its models handle biological knowledge. As a bio safety researcher, you will design and run capability evaluations against frontier models, generate and curate training data for safety classifiers, train and iterate on those classifiers alongside ML engineers, and measure how they hold up against adversarial pressure in production traffic. The work sits at the intersection of applied ML and biosecurity, translating threat models into evals, datasets, and deployed systems. The core technical tension is precision: safeguards need to be robust against sophisticated actors while staying out of the way of the far larger population of legitimate researchers using Claude to accelerate life sciences work. You do not need to be an ML researcher today; Anthropic is looking for strong scientific programmers with real depth in modern biology who want to bring that depth to bear on model evaluation and classifier development.

• Design, build, and run capability evaluations to assess what new models can do in the biological domain, and turn results into concrete deployment recommendations
• Develop training and evaluation datasets for safety classifiers, working with internal and external threat modeling experts to ground them in realistic risk
• Train, tune, and iterate on safety classifiers with ML engineers, optimizing jointly for adversarial robustness and low false-positive rates
• Build the tooling and pipelines that make evaluation and classifier development fast and repeatable
• Analyze classifier and eval performance against production traffic, identify gaps, and prioritize improvements
• Design and run red-teaming and stress-testing of safeguards as threats, models, and product surfaces evolve
• Partner with Research, Product, and Policy teams to embed biological safety throughout the model development lifecycle
• Contribute to external communications including model cards, blog posts, and policy documents
• Track developments in biology, ML, and biosecurity for their potential to create new risks or enable new mitigations

Minimum qualifications include strong proficiency in Python and an extensive background in scientific programming and data analysis; an excellent grasp of ML fundamentals; excellent knowledge of modern biology across both measurement and engineering (high-throughput assays and functional characterization, as well as gene synthesis, genome editing, strain construction, and protein engineering); the ability to build and maintain your own tooling; experience designing quantitative experiments or evaluations and drawing defensible conclusions from noisy results; strong analytical and writing skills; familiarity with dual-use research concerns and biosecurity frameworks such as select agent regulations, the Biological Weapons Convention, or Australia Group guidelines; and comfort with ambiguity and shifting priorities.

Preferred qualifications include experience working with large language models (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 or red-teaming, at least 8 years of hands-on experience in life sciences, and experience leading complex technical projects across multiple stakeholder groups.

Annual salary: $300,000—$405,000 USD. Minimum education: Bachelor's degree or an equivalent combination of education, training, and/or experience. Required field of study: a field relevant to the role. Location-based hybrid policy: all staff are expected to be in one of Anthropic's offices at least 25% of the time. Anthropic sponsors visas and retains an immigration lawyer to help.