AnthropicResearch
AI Ethics & Safety Researcher
San Francisco, CAHybridPosted 1 weeks ago
Full-timeSenior$190k - $320k
about this role
Conduct research on AI safety, alignment, and responsible AI development. Contribute to Constitutional AI and other safety approaches.
responsibilities
- •Conduct AI safety research
- •Develop evaluation frameworks for model safety
- •Collaborate on Constitutional AI improvements
- •Publish research papers
- •Engage with the broader safety community
requirements
- PhD in relevant field or equivalent experience
- Published research in AI safety or alignment
- Strong technical skills in ML
- Experience with language model evaluation
nice to have
- +Background in philosophy or ethics
- +Policy experience
- +Red-teaming experience
benefits
Mission-Driven WorkEquityHealth InsuranceSabbatical Program
required skills
AI SafetyResearchMachine LearningEthicsAlignment
quick apply
Apply directly on the company website.
about Anthropic
San Francisco, CA
Hybrid position