About Resolution

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.

Research at Resolution

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.

About the Role

You are the security architect for our research pipeline. You'll define how we securely conduct research across multiple cloud environments, partnering closely with engineering to make CI/CD, automated research agents, and large-scale compute secure by default. You would build a hardened environment where researchers and agents iterate at speed without risking data leakage, supply-chain compromise, and other security failures.

Resolution's work will involve sensitive frontier-relevant research and partnerships with AI labs. This role exists both to protect that work and to enable it: good security is what makes deeper lab partnerships possible. We draw a distinction between two closely related areas of security:

Research & infrastructure security. Securing how research actually runs: CI/CD pipelines, automated research agents, multi-cloud compute, and code/data/model-weight handling.
Corporate IT & security. The endpoint, identity, and collaboration scaffolding a distributed research org runs on, in combination with the compliance frameworks that unlock lab partnerships.

This role focuses on the former, covering security on the technical side of the organization. You would report to senior leadership and work closely with our security and engineering teams (as well as with our operations team).

In practice, we expect to grow the security team one hire at a time, so your initial set of responsibilities is likely to span both areas. We expect the distinction to clarify over time.

Responsibilities

Secure DevSecOps & CI/CD Orchestration

Pipeline Hardening: Build security guardrails directly into our CI/CD pipelines. Ensure that every deployment, whether manual or agent-driven, is automatically scanned, verified, and compliant.
Automated Verification: Establish workflows where our agents can test their own code and infrastructure changes against security policies before deploying to production environments.
Infrastructure as Code (IaC): Lead the implementation of "Compliance as Code." Automate the auditing and enforcement of security configurations across our AWS, GCP & neocloud footprints.

Supply Chain Security for Automated Research

Provenance and Integrity: In an environment where we rely heavily on automated coding agents, build systems to ensure the provenance of code and dependencies. Implement robust signing, SBOM (Software Bill of Materials) generation, and automated vulnerability management.
Agent Sandbox Security: Define and enforce security models for our research agents. Ensure that agents have the "least privilege" access required to execute experiments while remaining isolated from sensitive IP and credentials.

Multi-Cloud Research Infrastructure

Compute Security: Manage the security architecture for our high-compute research environments. We operate in a multi-cloud ecosystem; you will be responsible for consistent, zero-trust network segmentation and identity management across disparate cloud providers.
Research Data Protection: Develop and maintain the data handling protocols necessary for working with pre-publication research and potentially sensitive model weights.

Enabling Frontier Access

Compliance as a Competitive Advantage: Partner with AI labs to navigate security audits. You will bridge the gap between our "move fast" research culture and the high-bar security requirements of frontier model providers, turning compliance into an accelerator for our research agenda.

You May Be a Good Fit If You

Are a seasoned security engineer who writes code, with deep experience in Terraform, Kubernetes, and CI/CD tools (GitHub Actions, GitLab CI).
Have managed security across multiple cloud providers (AWS / GCP / neoclouds) and understand the nuance of securing ephemeral, high-compute research clusters.
Take a pragmatic approach to modern software supply chains and understand the unique risks of AI-driven development and how to mitigate them without killing velocity.
Understand the threat model of a high-value target for state-level actors and IP theft, and can build systems robust against sophisticated adversaries.
Can explain complex security trade-offs to lead researchers and scientists, saying "yes, safely" rather than just "no."
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.

Why This Role is Unique

At Resolution, "Corporate Security" is a separate function. This role is focused on the Research Infrastructure. You will be working at the frontier of how automated alignment research is actually done. You will be building the security primitives for a new way of doing science: one where humans and machines collaborate to solve the most important problem of the 21st century.

Application Process

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 Security Engineer 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.
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.

Logistics

Salary: Your salary depends on the scope, autonomy, and impact we expect you to have at Resolution. This role sits on our research compensation scale. The expected range of in-person salaries for this role is:

L4 (SWE II): $346,000
L5 (Senior SWE): $451,000
L6 (Staff SWE): $670,000
L7 (Senior Staff SWE): $930,000

We level using an internal adaptation of Google's standard levelling; the band above is indicative of where a strong candidate might come in.

Location: Berkeley, California. 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.

Security Engineer (Research Infrastructure)