Research Scientist, Propensity, Cyber and Autonomous Systems Team in London

The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action. We work with frontier developers and governments globally. Our resources, unique agility and international influence make this the best place to shape both AI development and government action.

Role Summary

Within the Cyber & Autonomous Systems Team (CAST) at AISI, the Propensity project studies unprompted or unintended model behaviour, particularly potentially dangerous behaviour: the propensity of a model to cause harm. Our current project is to study effect sizes of environmental factors on these propensities, e.g. whether models are consistently more willing to take harmful actions when their existence is threatened. Understanding model propensities is the key missing pillar in our overall picture of risk from autonomous AI.

What we are looking for

The Propensity project team currently consists of one research scientist and two research engineers. We are looking to add a second research scientist to help with challenges like those above, through discussion, written plans and designs, and writing or reviewing code that implements those designs.

The ideal candidate will have the following skills:

• A proven ability to identify and operationalise key uncertainties in a research area, and propose and improve on experimental approaches for collecting evidence on these uncertainties.
• Knowledge of and experience in selecting and applying statistical inference methods in order to draw risk-relevant and action-guiding conclusions from experimental evidence.
• Ability to engage critically with existing or proposed research methodology, assessing to what extent such critiques impact the central conclusions of the work.
• Strong enough Python knowledge to get hands-on with developing and iterating on our Inspect tasks.
• A sufficient understanding of transformer architecture and training dynamics to inform interpretations and predictions of their observable behaviour.

We expect these skills will be held by people with:

• 3+ years of experience in a quantitative research discipline involving experimental design and analysis.
• Experience writing Python code meeting quality standards.
• Professional or educational contact with LLMs and transformer theory.

What We Offer

• Impact you couldn't have anywhere else.
• Incredibly talented, mission-driven and supportive colleagues.
• Direct influence on how frontier AI is governed and deployed globally.
• Opportunity to shape the first & best-resourced public-interest research team focused on AI security.
• Resources & access including pre-release access to multiple frontier models and ample compute.
• Hybrid working, flexibility for occasional remote work abroad and stipends for work-from-home equipment.
• At least 25 days' annual leave, 8 public holidays, extra team-wide breaks and 3 days off for volunteering.
• Generous paid parental leave.
• On top of your salary, we contribute 28.97% of your base salary to your pension.

Selection process

The interview process may vary candidate to candidate, however, you should expect a typical process to include some technical proficiency tests, discussions with a cross-section of our team at AISI, and culminate in a conversation with members of the senior leadership team here at AISI.