BioSafety AI Research Engineer — Evaluations & Classifiers

Anthropic; San Francisco (CA); Hybrid; USD 300,000 - 405,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Office space in San Francisco

Job summary

Anthropic in San Francisco seeks a bio safety researcher to design and run capability evaluations for biology-focused models, build and curate datasets for safety classifiers, and iterate on those classifiers with ML engineers.

You will work at the intersection of applied ML and biosecurity, translating threat models into evals, datasets, and deployed systems, with emphasis on precision and robust safeguards.

Qualifications

• Strong proficiency in Python and scientific programming
• Solid understanding of ML fundamentals and development practices
• Extensive biology knowledge including assays and genome editing
• Ability to build and maintain your own tooling
• Experience designing quantitative experiments or evaluations
• Strong analytical and writing skills, able to explain concepts to non-technical stakeholders

Responsibilities

• Design, build, and run capability evaluations for biology models and turn results into deployment recommendations
• Develop training and evaluation datasets for safety classifiers with threat-model grounding
• Train and iterate on safety classifiers with ML engineers for robustness and low false positives
• Build tooling and pipelines to speed up evaluation and classifier development
• Analyze classifier and eval performance against production traffic and identify gaps
• Lead red-teaming and stress-testing of safeguards as models evolve
• Collaborate with Research, Product, and Policy teams to embed biology safety throughout development
• Contribute to external communications including model cards, blogs, and policy documents
• Track developments in biology, ML, and biosecurity for new risks or mitigations

Skills

Python

ML fundamentals

Biology knowledge

Experiment design

Communication

Independent working

Education

Bachelor's degree

Job description

Anthropic in San Francisco seeks a bio safety researcher to design and run capability evaluations for biology-focused models, build and curate datasets for safety classifiers, and iterate on those classifiers with ML engineers.

You will work at the intersection of applied ML and biosecurity, translating threat models into evals, datasets, and deployed systems, with emphasis on precision and robust safeguards.