[Hiring] Safety Research Scholar @Scale AI

Role Description

The Human Frontier Collective (HFC) brings researchers and scientists together to tackle consequential problems in AI. In partnership with Scale Labs, we are building a small cohort of researchers to work on the empirical foundations of AI safety.

Each scholar owns a substantial part of a safety research project, working alongside a mentor from the research question through the experiments to deciding what to test next.

Research Areas

• AI control and chain-of-thought monitoring: Developing techniques to oversee and constrain AIs, including detecting harmful intent or deception.
• Alignment auditing and evaluations: Building scalable methods to test whether models have hidden goals, misaligned behaviors, or unsafe tendencies.
• Multi-agent safety: Studying the risks that emerge when multiple agents interact, such as collusion, coordinated failures, or unexpected collective behavior.
• Recursive Self-Improvement (RSI) safety: Investigating how to keep AI systems safe and aligned as AIs increasingly contribute to their own development.
• Science of Evaluations: Examining when and how models recognize they're being tested, and how situational awareness affects the reliability/validity of evaluations.
• Misuse risks and evaluations: Developing methods to assess how AI systems could be exploited by malicious actors, including evaluating their potential to enable harmful activities.

Representative Research

• ASPI: 728 task–attack scenarios testing how clarification-seeking changes prompt-injection vulnerability in LLM agents.
• PropensityBench: Simulating real-world pressure to choose between safe or harmful behavior.
• BioRiskEval: Evaluating whether safeguards for open-weight bio-foundation models remain robust under fine-tuning and probing.

What You'll Do

• Projects are mentor-guided, with a list of research proposals matched to your research interests and background.
• Own research end to end: Turn a high-level safety question into hypotheses, baselines, and controlled experiments.
• 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, and decide what to try next without step-by-step direction.
• Make the work legible: Produce reproducible code, experiment logs, analysis, and precise technical writing.

Who We're Looking For

• Motivated by reducing catastrophic risks from advanced AI systems.
• Interested in technical safety research, such as alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety.
• Pursuing or have completed a PhD in CS, ML, statistics, mathematics, or a related field (equivalent track record encouraged).
• Can make progress with high-level guidance, including implementing, debugging, interpreting results, and proposing next experiments.
• Communicate research clearly and handle confidential information responsibly.

Application Process

• Submit your resume or CV, your Google Scholar profile if you have one, and one research project you substantially owned, with 2–3 sentences on your contribution.
• Walk us through a past project, including what you tried, what didn't work, and what you learned.
• Work through a research problem with us and propose how you'd approach it.
• Successful candidates complete the applicable recruiting, work-authorization, security, and project-onboarding steps.