AI Safety Residency — Scale Labs Preparedness & Policy (SLPreP)
Scale AI · Canada; United Kingdom; United States
Team: Human Frontier Collective
Posted: 2026-10-16
Pay: USD 100 – USD 100 per hour
The AI Safety Residency program focuses on conducting empirical research to improve the evaluation and safeguarding of frontier AI systems. Residents are responsible for designing and executing end-to-end research projects, building evaluation harnesses, and producing technical outputs suitable for top machine learning conferences. Candidates should possess or be pursuing a PhD in a quantitative field and demonstrate strong research judgment in areas such as alignment, AI control, or multi-agent safety.
Skills & tags: ai safety, machine learning, alignment research, red teaming, empirical research, llm evaluation, ai control, multi-agent systems, statistics, computer science
View and apply at the original posting
Postings belong to their employers; this page links to the source.