Resolution does research on how to align artificial superintelligence (ASI). ASI may be developed in the next few years, but it is unclear whether alignment is on track to be ready in the same timeframe. We aim at higher a priori confidence in aligned outcomes by pursuing a portfolio of theory and empirics bets, any one of which — if it succeeds — would meaningfully advance the field. We invest heavily in research automation to accelerate progress, and we believe that stronger alignment theory unlocks higher automation: more principled approaches give us better filters for which directions of automated research are promising.
Resolution was founded in May 2026 by researchers from UK AISI's Alignment Team, who ran the £30m Alignment Project, and Timaeus, who pioneered applying singular learning theory to alignment.
For more information, see our announcement.
We work across a portfolio of research areas, currently including:
Scalable oversight: empirical work on protocols (debate, recursive reward modeling, prover-verifier games) that allow weaker overseers to supervise stronger systems, paired with complexity-theoretic work on equilibria and reachability.
Complexity theory: theoretical work on modeling the interaction of superintelligent agents with lower complexity training environments, including applications to scalable oversight, heuristic arguments, and other agendas.
Learning theory: singular learning theory and its applications, deep learning theory, computational mechanics, etc.
Personas: theory and empirics of low-dimensional structure within model behavior across training and token dimensions.
The full set of bets has not yet been finalized but, in the future, may include further agendas like:
Heuristic arguments: mechanistic understanding of what models know, low-probability estimation.
Game theory: mechanism design, agent foundations, open-source game theory.
A cross-cutting focus is research automation: building infrastructure and tooling to scale all of the above by leveraging AI research assistants at every level of the stack, across both theoretical and empirical work.
As a Research Scientist at Resolution, you'll work as part of a research program led by a senior researcher (which could be you!). We're hiring across our research programs, and the team you'd join depends on your strengths and interests — in your application, indicate which program(s) you'd be most interested in.
Our goal of reaching higher confidence in alignment will require significant new contributions in both methods and scientific understanding. The work you do day-to-day will be part of a collaborative research program; all programs involve deep technical research, with strong support for cross-program collaboration. We welcome both empirical and theoretical profiles.
Research within your program: both translating and modelling alignment problems into concrete empirical or theoretical form and executing on the resulting concrete problems. Execution means designing and running experimental protocols and methods for empirics, and proving, conjecturing, and investing in autoformalization for theory.
Writing and presentation of completed research in the form of papers, blog posts, and talks.
Communication of research progress and obstacles to members of your team through channels like Slack on a daily basis and in weekly meetings.
Have a graduate degree (Ph.D.) or equivalent experience in a field relevant to the program you're applying to: ML, CS, mathematics, physics, statistics, philosophy, or something closely related
Have a track record of research and strong technical writing ability: papers, preprints, or comparable output
Have a strong mathematical background, even if your work is primarily empirical
Can credibly articulate why your area of alignment work is worth pursuing
Are willing to use AI tools aggressively in your own workflow, with appropriate care to not get fooled!
Are motivated by alignment of artificial superintelligence (ASI) and want to contribute to it full-time
(For scalable oversight) Hands-on experience with debate, prover-verifier games, RLHF empirics at frontier scale; familiarity with the scalable oversight literature; background in game theory, complexity theory, mechanism design, or decision theory
(For complexity theory) Demonstrated expertise in theoretical computer science, including creative modeling and assumption generation
(For learning theory) Background in algebraic geometry, Bayesian statistics, information theory, statistical physics, optimization theory, or learning theory; familiarity with (singular) learning theory
(Across programs) Experience scaling experiments to billion-plus parameter models; a track record of productive collaboration with engineers; prior engagement with our research or sibling organizations (Simplex, ARC, etc.). Experience with AI alignment is a plus, but is not a requirement: we are excited to bring experienced researchers from other fields into alignment work, and we see our ability to facilitate that transition as one of Resolution's comparative advantages.
We're also building out program leadership across our research areas. We expect to fill these roles primarily through targeted headhunting rather than open applications. If you think you might be a strong fit for a Research Program Lead position, a senior researcher who could direct an entire research program at Resolution, please reach out to us directly.
More excited about multiplying a research team than running the experiments yourself? Our Research Operations track (under Operations Staff) is about partnering with program leads on strategy, getting results to where they matter, and unblocking researchers day to day. And if you're drawn to the infrastructure and tooling behind the science as much as the science itself, take a look at Research Engineer.
Intro chat. <20-minute conversation to understand your background, motivations, and ideas, and to answer questions you may have about logistics.
Take-home assessment(s). 4-8 hours across 1-2 assessments that simulate working as a Research Scientist at Resolution. We find that assessments like these provide some of the strongest evidence about future performance, and so we truly appreciate your time in completing these tasks. We’ll compensate you for your time, subject to right-to-work constraints. The exact format of the assessments is liable to change, but may involve some but not all of the following:
(~4h) Writing a research plan in response to an open-ended research prompt.
(~4h) Designing and running experiments in response to a narrower research prompt.
(~4h) Preparing and giving an interactive talk on a research/engineering project you’ve conducted in the past. (This would be at a later stage.)
(~1h) Solving technical coding problems via a platform like CodeSignal. We have not yet decided whether to conduct coding examinations, but if we do, it would only be for more engineering-heavy roles.
Interview on take-home assessments. We’ll typically follow up assessments with a 45-minute interview to explore how you work through new problems.
Final interview. Interview on your career history, accomplishments, and skills with a senior researcher in our organization.
Work trial. 2-5 days working with us on real problems to assess mutual fit.
Reference checks. Towards the very end of this process, we will, in parallel, reach out for references from past employers.
Timeline. We’re trying to run this process quickly. Our target is a ~1.5-month turnaround from submission to offer. This will mean approximately one week per stage (with the exception of the take-home assessments, which will span 2–3 weeks). Some stages may end up running in parallel. To speed this up further, we will also fast-track exceptional candidates, for instance, by skipping the assessment stage or work trial.
Salary: Your salary depends on the scope, autonomy, and impact we expect you to have at Resolution. The expected range of in-person salaries for this role is:
L3: $236,000
L4: $346,000
L5: $451,000
L6: $670,000
L7: $930,000
Strong early-career researchers will typically come in at L3. Someone with several years of independent research experience would likely start at L4 or L5.
Location: Berkeley, California is strongly preferred; London is a secondary hub; remote may be considered in exceptional cases.
Benefits:
5 weeks of paid vacation per year, in addition to public holidays.
Comprehensive healthcare insurance (medical, dental, vision).
Unlimited sick leave to prioritize your well-being.
An unconditional 401(k) contribution equal to 4% of your salary.
Visa sponsorship: We can sponsor visas for relocation to Berkeley.
Minimum education: A bachelor's degree in a field relevant to the role, or an equivalent combination of education, training, and/or professional experience that demonstrates comparable knowledge.
Deadline: Applications are rolling — we'll respond within one week of receipt.
Start date: ASAP.
Compensation Range: $236K - $930K
