Safety Research Scholar - Human Frontier Labs

📋 Description

• Own research end to end: Turn a high-level safety question into hypotheses, baselines, and
• Build the measurement: Implement and debug evaluation harnesses, agent environments, datasets
• Exercise research judgment: Identify confounds, separate what a model can do from what it tends to
• Make the work legible: Produce reproducible code, experiment logs, analysis, and precise technical

🎯 Requirements

• Are motivated by reducing catastrophic risks from advanced AI systems
• Are interested in technical safety research, such as alignment evaluations, AI control, monitoring
• Are pursuing or have completed a PhD in CS, ML, statistics, mathematics, or a related field (we
• Can make progress with high-level guidance, including implementing, debugging, getting unstuck
• Communicate research clearly and handle confidential information and internal systems responsibly