Research Scientist

Berkeley, California, Remote. Posted 4 months ago

The role

Research Scientists will conduct deep technical research within a collaborative program. This involves translating and modelling alignment problems into empirical or theoretical forms and executing research through experimental protocols or autoformalization.

What you will do

Research within your program by translating and modelling alignment problems
Design and run experimental protocols and methods for empirics
Prove, conjecture, and invest in autoformalization for theory
Write and present research in papers, blog posts, and talks
Communicate research progress and obstacles via Slack and weekly meetings

Required qualifications

Graduate degree (Ph.D.) or equivalent experience in a field relevant to the program (ML, CS, mathematics, physics, statistics, philosophy, or closely related)
Track record of research and strong technical writing ability
Strong mathematical background
Ability to credibly articulate why your area of alignment work is worth pursuing
Willingness to use AI tools aggressively in your workflow
Motivation to contribute to alignment of artificial superintelligence (ASI) full-time
Bachelor's degree in a field relevant to the role, or an equivalent combination of education, training, and/or professional experience

Nice to have

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
Demonstrated expertise in theoretical computer science, including creative modeling and assumption generation
Background in algebraic geometry, Bayesian statistics, information theory, statistical physics, optimization theory, or learning theory
Familiarity with (singular) learning theory
Experience scaling experiments to billion-plus parameter models
Track record of productive collaboration with engineers
Prior engagement with our research or sibling organizations (Simplex, ARC, etc.)
Experience with AI alignment

Benefits

5 weeks of paid vacation per year, in addition to public holidays
Comprehensive healthcare insurance (medical, dental, vision)
Unlimited sick leave
Unconditional 401(k) contribution equal to 4% of your salary

Before you apply

As of November 5, 2026, only applications for Scalable Oversight are being reviewed
We can sponsor visas for relocation to Berkeley
Initial screener is a 15-minute conversation
Work test involves a 4-hour take-home assignment
Process includes experience interview and leadership 1:1

About the company

Resolution does research on how to align artificial superintelligence (ASI). The company was founded in 2026 by researchers from UK AISI's Alignment Team and Timaeus.