AI Safety Residency — Scale Labs Preparedness & Policy (SLPreP)
Canada · United Kingdom +1
$100 an hourOn-site
Job details
- Canada · United Kingdom +1
- On-site
- $100 an hour (posted by the company)
- Full-time
- Human Frontier Collective
- Posted 1 month ago
Sponsorship history
Past filings by Scale AI in public government data. Not a promise of sponsorship.
- Filed 8 H-1B LCAs in FY2025
Full job description
About the Program
The Human Frontier Collective (HFC) brings researchers and scientists together to tackle consequential problems in AI. In partnership with the Preparedness and Policy research team, we are building a small cohort of researchers to work on the empirical foundations of AI safety.
The work includes thinking about various failure modes, evaluating whether safety controls hold up under pressure in realistic settings, and studying how AI agents (mis-)behave over long-horizon tasks. Residents take open research questions like these and turn them into work that improves how frontier AI systems are evaluated and safeguarded.
Research Areas
Mentors will guide AI safety residents on projects in AI safety research areas, such as:
- AI control and chain-of-thought monitoring: Developing techniques to oversee and constrain AI systems, including monitoring their reasoning to detect harmful intent or deception.
- Alignment red-teaming: Developing science around testing 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: Developing methods to assess how AI systems could be exploited by malicious actors, including evaluating their potential to enable harmful activities.
Projects are matched to demonstrated expertise; we don’t expect any candidate to cover every area.
Representative Research
- ASPI: A benchmark with task–attack scenarios testing how clarification-seeking changes prompt-injection vulnerability in LLM agents.
- PropensityBench: evaluating whether language models choose harmful actions when given simulated dangerous tools under various operational pressures
- BioRiskEval: evaluating whether safeguards for open-weight bio-foundation models remain robust under fine-tuning and probing.
- RSI Control: evaluating whether frontier models can covertly sabotage R&D efforts in the RSI loop.
See more work from the Human Frontier Collective.
