Security Engineer (Corporate IT)

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 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.

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 latter, covering security on the operational side of the organization. You would report to senior leadership and work closely with our security and operations teams (as well as with our engineering 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.

We are looking for a hands-on, strategic leader to build and own our Corporate IT and Security function from the ground up. As we scale from our current team to 40–60 FTEs over the next two years, you will be the single point of accountability for ensuring our researchers have the tools they need to move fast while maintaining a security posture that earns the trust of external partners and AI labs.

We are looking for a builder, not just a manager. You should be comfortable getting into the weeds of configuration and implementation, but you understand that your ultimate goal is to enable world-class research through secure infrastructure.

1. Identity and Access Management (IAM)

• Implement a robust Zero-Trust architecture. You will define the lifecycle of identities for our staff, collaborators, and automated research agents.

• Ensure rigorous access control management, balancing the open-science nature of our publication goals with the extreme sensitivity of our pre-publication research and model access requirements.

2. Communications and Email Security

• Secure our communication channels. As an organization that may become a high-value target for state actors and competitive intelligence gathering, you will implement advanced email security, phishing protection, and secure collaborative workflows.

3. Security Architecture as an Enabler

• Act as the primary bridge between our research needs and the security requirements of external AI labs.

• Help us navigate the security audits required to gain and maintain access to frontier models, turning compliance into an accelerator for our research agenda.

• Are a hands-on operator with a technical background and are comfortable configuring systems, scripting automation, and personally setting up the stack.

• Understand the threat model of a high-stakes research organization and can balance extreme security with an AI lab's "move fast" requirements.

• Have built an IT and/or security function from scratch and can operate with autonomy and ambiguity in an early-stage org.

• Can translate technical security requirements into plain English for researchers, theorists, and leadership.

• Are familiar with compliance frameworks (SOC 2, ISO 27001) and partner-lab security requirements.

• 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.

At most organizations, IT and Security are viewed as overhead. Here, your work is a core component of the research strategy. By securing our operations, you enable the collaboration and external partnerships that allow our researchers to access sensitive models and data to accelerate progress. You will help define the operational security standards for a new generation of AI safety organizations.

1. Application review. Every application gets at least one human review.

2. CodeSignal (45 minutes, in two sections). A security-specific assessment, not LeetCode and not a general coding test: it involves very little writing code by hand, and leans instead on code review and written responses to scenarios like diagnosing failures in an IAM configuration. We want the content of our assessments to have at least some overlap with the things we expect you to do in real life.

3. Screening call (15 minutes). An informal chat, where we briefly cover background, fit, and motivation.

4. Technical and experience interviews (about 2-3 hours in total, across two or three sessions). We're still settling the exact shape of these for this role, and we'll tell you the format before each session. Expect some combination of: a technical interview on reading and diagnosing unfamiliar infrastructure, without AI assistance; a technical interview in two parts, an AI-unassisted design and specification problem followed by an AI-assisted implementation of it; and an experience interview walking through one or more past projects in detail, with time to discuss the role and answer your questions.

5. 1-on-1s. A chat with our chief scientist, Geoffrey, as well as any relevant people from the team you would like to talk to and ask questions.

6. References. We'll reach out to a few references as we make our final decision.

On scheduling. Where we can, we'll bundle the sessions in (4) so they occur back to back, though with different interviewers, so you get a chance to talk to more of our team. We'll also run (5) and (6) in parallel. Our aim is to get you an update within 2-3 days of each stage, which means a process of about three weeks. For some candidates, especially if you have competing deadlines, we'll aim to push faster.

On the technical interviews. We dropped work tests because there's so little signal left in them. What we're looking for is how well you figure out what to tell the AIs, how well you interact with the AIs throughout implementation, and how well you navigate the resulting outputs. The exact details of the tests are still being settled for this role, but what we're testing for will remain the same.

On interviewers. Most of our interviewers are on our engineering team, and we'll try to set things up so that you get to talk to different people at each interview. Each interview will have time for you to ask questions.

Salary: Your salary depends on the scope, autonomy, and impact we expect you to have while working at Resolution. 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't guarantee visa sponsorship, though this will be possible in some circumstances.

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.

Timeline: Applications are reviewed on a rolling basis, with priority given to those who apply early, so please apply ASAP. We'll respond to applications within two weeks of receipt.

Start date: ASAP.

AI Usage

We may use automated systems and AI tools to support recruiting and hiring activities. Final hiring decisions are made by human decisionmakers.