Skip to main content
All jobs

Employer listing

AI Safety Residency - SLPreP

Scale AI

remote · internship · Intern

Salary not specified

About the Program

The Human Frontier Collective (HFC) brings researchers and scientists together to tackle consequential problems in AI. In partnership with Scale Labs Preparedness and Policy (SLPreP), 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.

What You'll Do

Projects are mentor-guided. Each resident will be given a list of research proposals and matched with one based on research interests and background. You'll meet weekly with a researcher from SLPreP who sets direction and gives feedback, while driving day-to-day work. Projects are expected to result in a conference paper submitted to top ML conferences (NeurIPS, ICML, ICLR).

  • Own research end to end: Turn a high-level safety question into hypotheses, baselines, and controlled experiments, producing 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.
  • Make the work legible: Produce reproducible code, experiment logs, analysis, and precise technical writing.

Who We're Looking For

  • Motivated by ensuring the safe and responsible development of advanced AI systems.
  • Interested in technical safety research (alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety).
  • Pursuing or completed a PhD in CS, ML, statistics, mathematics, or a related field (or an equivalent track record).
  • Ability to make progress with high-level guidance, including implementing, debugging, interpreting results, and proposing next experiments.
  • Strong research communication skills and responsible handling of confidential information.

Role Details

  • Location: Remote within the United States (including California and New York), Canada, or the United Kingdom
  • Hours: 20 hours per week
  • Term: 3 months, with the option to extend to 6–12 months for exceptional candidates (part-time internship structure)
  • Compensation: $100/hour

Application Process

  1. Apply: Submit resume/CV, Google Scholar profile (if available), and one substantially owned research project with 2–3 sentences on your contribution.
  2. ML research take-home: Turn a high-level research question into testable hypotheses, design/run small-scale experiments, and write up findings and interpretations.
  3. Research discussion (30 min): Open-ended discussion on key questions and promising directions in AI safety.
  4. Hiring manager chat (15 min).