Job description
Redwood Research • San Francisco Bay Area
San Francisco Bay Area
- In this role, Redwood Research staff think carefully about threat models associated with AI, analyze countermeasures, and communicate their results.
- Analyse threat models of artificial intelligence systems and identify potential vulnerabilities.
- Develop and test countermeasures for identified AI threats using empirical methods.
- Communicate findings through research papers, focusing on safety and alignment of AI.
- Collaborate with the team to ensure AI systems are developed with safety and ethics in mind.
Redwood Research is a nonprofit conducting exploratory AI alignment research.