N
AI Safety Researcher (Alignment)
Northwind Labs · San Francisco, CA
SafetyMidHybridFull-timeNonprofit
Posted Jun 2, 2026
Run empirical experiments on scalable oversight and model behavior for advanced AI systems.
What AI systems or risks this role involves
Frontier LLMs evaluated for deceptive alignment, scheming, and reward hacking — work informs deployment policy decisions.
About the role
Join our alignment team to design experiments that improve our ability to oversee increasingly capable models.
We care about empirical rigor, clear writeups, and contributions to the broader safety community.
Get roles like this delivered weekly
Subscribe to The Governance Stack.
Beehiiv signup embed
Replace this block with the Beehiiv embed code for The Governance Stack.