
Safety Research Scholar - Human Frontier Labs
AI
The Human Frontier Collective, in partnership with Scale Labs Preparedness and Policy, is building a small cohort of researchers to work on the empirical foundations of AI safety. Residents will pursue mentor-guided research projects on topics such as AI control, alignment red-teaming, multi-agent safety, and evaluation science, with the goal of producing a conference paper. Candidates should be pursuing or have completed a PhD in CS, ML, statistics, mathematics, or a related field, or have an equivalent track record.
What you'll do
- Own research end to end: turn a high-level safety question into hypotheses, baselines, and controlled experiments, and produce work that others can inspect and build on.
- Build the measurement: implement and debug evaluation harnesses, agent environments, datasets, monitoring methods, or post-training experiments.
- Exercise research judgment: identify confounds, separate what a model can do from what it tends to do, make sense of negative results, and decide what to try next without step-by-step direction.
What you need
Must-have
AI safety researchAlignment evaluationsAI controlChain-of-thought monitoringRed-teamingMulti-agent safetyRecursive Self-Improvement safetyScience of Evaluations
Soft skills
Research judgmentClear communicationIndependent problem-solvingResponsibilityConfidentiality
AI safetyResearchMachine LearningRemoteVolunteerPhDAlignmentEvaluations