AI Safety Residency - SLPreP

The role

Residents will conduct empirical AI safety research by turning high-level questions into hypotheses, baselines, and controlled experiments. The work involves building measurement tools and producing research papers for top ML conferences.

What you will do

• Own research end to end
• Turn high-level safety questions into hypotheses, baselines, and controlled experiments
• Implement and debug evaluation harnesses, agent environments, datasets, monitoring methods, or post-training experiments
• Identify confounds and interpret results
• Produce reproducible code, experiment logs, analysis, and precise technical writing
• Submit research papers to top ML conferences

Required qualifications

• Motivated by ensuring the safe and responsible development of 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
• Can make progress with high-level guidance
• Can communicate research clearly
• Can handle confidential information and internal resources responsibly

Nice to have

• Researchers with an equivalent track record

Before you apply

• Submit resume or CV
• Submit Google Scholar profile if you have one
• Submit one research project you substantially owned, with 2–3 sentences on your contribution
• Complete an ML research take-home
• Participate in a research discussion and a hiring manager chat

About the company

Scale develops reliable AI systems for important decisions, providing data and full-stack technologies to power leading models. They work with industry leaders, enterprises, and government agencies.