Job description
MATS Research • San Francisco Bay Area, London, UK
San Francisco Bay Area, London, UK
$23,400 stipend
- In this role, you'll complete a ~20 hour AI safety research project and submit a detailed write-up of your findings.
- Identify and research an interesting question aligned with pragmatic interpretability or applied safety approaches.
- Develop hypotheses, gather evidence for and against them, and rigorously sanity-check all results.
- Write an executive summary with graphs and concrete details about your methodology, findings, and key takeaways.
- Complete application form responses demonstrating clear communication, critical thinking, and strong research taste.
Machine Alignment, Transparency, and Security (MATS) Research is an educational seminar and independent research program that aims to provide talented scholars with talks, workshops, connections, and research mentorship in the fields of AI alignment and AI governance.