BioSafety AI Research Scientist — Safety & Evaluation

Anthropic Limited

San Francisco (CA)

Presencial

USD 300.000 - 405.000

Tempo integral

Há 11 dias

Uma candidatura completa em um minuto

Currículo e carta de apresentação personalizados, prontos para serem enviados.

Passe pelos filtros ATS

Resumo da vaga

Anthropic Limited is seeking a bio safety researcher to design and run capability evaluations for how our models handle biological knowledge, and to develop safety classifiers trained with biology data. You will work with ML engineers to iterate on classifiers, measure robustness under adversarial traffic, and help embed biological safety into the full model development lifecycle.

You don't need to be an ML researcher today; strong scientific programming and biology depth are valued.

Qualificações

  • Bachelor’s degree or equivalent in a relevant field.
  • Minimum field of study relevant to the role.
  • Location-based hybrid policy requires in-office presence at least 25%.
  • Visa sponsorship available, subject to conditions.

Responsabilidades

  • Design, build, and run capability evaluations for biology domain and translate results into deployment recommendations.
  • Develop training and evaluation datasets for safety classifiers, collaborating with threat modeling experts.
  • Train, tune, and iterate on safety classifiers with ML engineers, balancing adversarial robustness and false positives.
  • Build tooling and pipelines that speed up evaluation and classifier development.
  • 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 evolve.
  • Partner with Research, Product, and Policy teams to embed biological safety throughout the model lifecycle.
  • Contribute to external communications including model cards, blog posts, and policy documents.
  • Track developments in biology, ML, and biosecurity for risks and mitigations.

Conhecimentos

Python
ML fundamentals
Biology knowledge
Tooling
Experimental design
Writing
Biosecurity
Adaptability
Collaboration
Results-driven
Fast-paced work

Formação

Bachelor's degree in a relevant field
Minimum field of study relevant to the role

Descrição da vaga

Anthropic Limited is seeking a bio safety researcher to design and run capability evaluations for how our models handle biological knowledge, and to develop safety classifiers trained with biology data. You will work with ML engineers to iterate on classifiers, measure robustness under adversarial traffic, and help embed biological safety into the full model development lifecycle.

You don't need to be an ML researcher today; strong scientific programming and biology depth are valued.

Obtenha sua revisão de currículo grátis e confidencial.

ou arraste e solte seu arquivo aqui.

Similar jobs

Vagas similares que valem a pena comparar

Research Manager, Biological Safety
Research Manager, Biological Safety

EngineersOfAI • San Francisco (CA)

Presencial
USD 320.000 - 480.000
Biological Safety Research Manager
Biological Safety Research Manager

EngineersOfAI • San Francisco (CA)

Híbrido
USD 320.000 - 480.000
Senior AI Safety Scientist — Biology Risk (Remote US)
Senior AI Safety Scientist — Biology Risk (Remote US)

SecureBio, LLC • EUA

Remoto
USD 235.000 - 300.000
Healthcare coverage
Flexible work hours
Conference sponsorships
+1
AI Biology Safety Scientist & Model-Risk SME
AI Biology Safety Scientist & Model-Risk SME

Google LLC • Mountain View (CA)

Presencial
USD 174.000 - 252.000
Research Manager, Biological Safety
Research Manager, Biological Safety

Anthropic Limited • San Francisco (CA)

Híbrido
USD 405.000 - 485.000
Equity donation matching
Generous vacation and parental leave
Flexible working hours
+1
Life Sciences AI Research Engineer
Life Sciences AI Research Engineer

Anthropic Limited • San Francisco (CA)

Híbrido
USD 350.000 - 500.000
Equity donation matching
Generous vacation and parental leave
Flexible working hours
Senior AI Biosecurity Scientist — Remote, Flexible PTO
Senior AI Biosecurity Scientist — Remote, Flexible PTO

SecureBio, LLC • Cambridge (MA), Berkeley (CA)

Híbrido
USD 235.000 - 300.000
Flexible work hours
Unlimited paid time off (PTO)
Parental leave (12 weeks)
Research Scientist/Engineer, Biological Safety
Research Scientist/Engineer, Biological Safety

Anthropic Limited • San Francisco (CA)

Presencial
USD 300.000 - 405.000
Biosecurity AI Safety Enforcement Analyst
Biosecurity AI Safety Enforcement Analyst

Anthropic Limited • Washington, Baltimore (MD)

Híbrido
USD 245.000 - 285.000
Senior Biology Safety Analyst - Biosecurity & AI
Senior Biology Safety Analyst - Biosecurity & AI

TaskUs • Austin (TX)

Remoto
USD 100.000 - 160.000