PIBBSS | Research Residency 2026

The Residency

Application Deadline: November 2, 2025, at 11:59 PM Anywhere on Earth (AoE). Early application decisions will be made on a rolling basis before then.

Researchers-in-Residence will explore mathematical approaches to AI alignment, in collaboration with established Mentors with proven track records of connecting deep mathematics with empirical machine learning.

• Duration: 6 weeks, full-time, January 5–February 13, 2026
• Location: The London Initiative for Safe AI (LISA), London, in person (with a remote option for exceptional applicants, for compatibility with existing academic roles)
• Stipend: $6,000–$15,000, depending on seniority

The Residency will include speaker events and a research retreat.

What You’ll Be Doing

Researchers-in-Residence will, by default, spend 6 weeks in person in London at LISA working on AI alignment, in collaboration with Mentors. Project Mentors are established researchers in mathematics and AI alignment.

Individual projects will differ in scope and content, depending on the Resident’s research background; projects will begin lines of research in mathematical AI alignment. The intended end product of the Residency is a fleshed-out research proposal. You will spend 6 weeks doing mathematical research that builds on your existing research background, with the support of a project Mentor. You will work inside of or develop a new direction of applied-mathematical AI alignment research in order to assemble the research proposal deliverable.

At the end of the Residency, Iliad will help Researchers-in-Residence submit proposals to outside funders to spin up new research groups or to support other research projects (at PIBBSS, in academia, or independent). The funding ecosystem for technical academic researchers pivoting into AI alignment is vast. AI alignment is a ballooning field of research that is just crystallizing its earliest general theoretical results. Academics are extremely well positioned to contribute to this crystallization of the formal machinery; funders recognize this, and Iliad aims to facilitate that connection between academics branching into AI alignment and philanthropic donors (including state actors) supporting that research work. We are here to help you get a grip on this ecosystem, in the belief that great researchers with high academic standards are a crucial input in growing AI alignment into a fully developed scientific field. We will guide Residents in developing research proposals for submission to organizations such as Open Philanthropy, the Survival and Flourishing Fund, Schmidt Sciences, and the UK AI Security Institute (AISI); we aim to secure independent funding for projects for an additional 6–24 months.

Projects

Project descriptions are below. These are generally not binding, though some directions (*) are currently more developed than others, and these more established directions may involve working with existing teams. The remaining projects leave the field more open and are for you to develop.

• Simplicity and Degeneracy*
• Universal Predictors*
• Causality*
• Abstractions and Coarse-graining*
• Lossy Compression and Sparse Coding
• Computational Mechanics*
• Algorithmic Statistics*
• Heuristic Arguments*
• ReLU Neural Networks and Polyhedral Geometry*
• Gradient Flow and Morse Theory*
• Training Dynamics (SGD)*
• Free Energy and Conductance*
• Fokker–Planck*
• Renormalization and Interpretability*
• Rational Beliefs
• Irrational Beliefs
• Rational Preferences
• Irrational Preferences
• Sub- and Superagents
• Universal Agents*
• Embedded Agency and Decision Theory
• Boundaries and Interfaces*
• From Atoms to Agents
• Selection Theorems
• Bellman Operators and Reinforcement Learning
• Non‑Episodic Learning and Metacognition
• Backdoors and Interpretability*
• Reward and Value Learning*
• Social Choice and Voting*
• Goal Misgeneralization*
• Deception and Doom
• Control and Cybernetics
• Debate and Scalable Oversight*
• Tiling, Delegation, Reflection
• Extrapolated Volition

About You

Our competitive applicant is a PhD or postdoctoral researcher in mathematics, theoretical physics, theoretical computer science, or a related discipline, or someone with equivalent research experience. We welcome applicants with substantially greater research experience as well, and will tailor scope and compensation to suit that background.

If you have substantial research experience but are unsure about your fit, we encourage you to err on the side of applying!

Apply

We are accepting applications on a rolling basis before the November 2 deadline. If you are interested, please apply as soon as possible and we will be able to give you an early decision. We accept applicants from all countries.

The Residency is most centrally aimed at PhD and postdoctoral researchers. However, we encourage interested individuals with substantial prior research experience in their field of expertise to apply, regardless of credentials. The first stage of the application is designed to be easy to complete.

If you are uncertain about whether you would be a good fit for the program, please err on the side of applying. Feel free to contact us at recruiting@iliad.ac with any questions.

Source and application: https://pibbss.ai/pibbssxiliad-research-residency/