ScenarioSuperintelligence control and containment assurance

Superintelligence Intervention Protocol Designer

Also called SI Shutdown Protocol Designer

A Superintelligence Intervention Protocol Designer would specify who may intervene in a broadly superhuman system, how, and whether it would work. It depends on how AI develops, and no company is hiring for it now.

What they do

The work would start from a scenario in which a system far exceeds expert human groups. The designer would write intervention and continuity procedures: who has authority to pause, restrict or shut down a system, under what triggers, and what keeps essential services running afterwards. They would test each procedure on paper against a system that might resist, deceive or route around it. They would work with control researchers, security engineers, legal teams and oversight bodies. Each protocol would carry a feasibility assessment that says what has been shown, what is assumed and what is unknown.

What a strong hire delivers

In the first months, a strong hire would produce a small set of conditional intervention protocols tied to named scenarios and clear authority chains. Each would come with an honest feasibility assessment. They would also set out which claims are untested, agree escalation roles with leadership and oversight parties, and give the company a plain view of where its intervention capability is credible and where it is only asserted.

How you can tell they are good

Ask them to take one protocol and explain how it could fail. A strong candidate separates technical feasibility from institutional authority, names assumptions without prompting and says what evidence would change their mind. Ask who would be allowed to press the button and why others would accept it. Be wary of anyone who treats a written procedure as proof of capability.

Why it is hard to fill

If this role emerged, almost nobody would have done it. No established title exists, and no validated toolkit exists. The work sits between control research, security, formal methods, system safety and institutional design, and few people span even two of those. Candidates would also need the discipline to say what is not known. Most would come from adjacent fields and need time to learn the rest.

Where to find them

Today the nearest people work in AI control research, security engineering, formal verification and system safety. Some come from safety-critical industries where shutdown and continuity procedures are routine. Others work in AI governance and assurance, or in frontier scenario analysis at research groups, safety institutes and model providers. Look for people who have written procedures that were actually tested, not only papers.

Interview questions for a Superintelligence Intervention Protocol Designer

  1. Tell us about a shutdown or intervention procedure you designed. How did you establish that it would work?

    A strong answer describes real testing, exercises or verification, and admits limits. Worry if they describe only documents, or confuse approval of a procedure with evidence that it works.

  2. Who should hold authority to intervene in a very capable system, and how would you stop that authority being bypassed?

    Look for clear thinking on legitimacy, accountability, separation of duties and external oversight. Worry about answers that rely on one person, or ignore how the system itself might influence the decision makers.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are exploring how we would keep credible intervention capability over highly capable AI systems. We would need someone to specify who can intervene, how, and whether it would actually work. You would write conditional protocols and test them honestly against hard scenarios.

What you will do

  • Draft conditional intervention and continuity protocols for defined scenarios
  • Write feasibility assessments that separate evidence from assumption
  • Define authority chains, triggers and escalation roles with leadership
  • Stress-test protocols against systems that might resist or deceive
  • Work with control, security and legal colleagues on practical constraints
  • Brief external overseers on what our intervention capability can and cannot do

What you will bring

  • Demonstrated work in AI control, security, formal verification or system safety
  • Experience writing procedures that were tested, not only documented
  • Clear thinking about institutional authority and accountability
  • Ability to state uncertainty plainly in writing
  • Comfort working without an established toolkit
  • Collaborates well across technical, legal and governance teams

Nice to have

  • Experience with safety-critical shutdown or continuity planning
  • Background in AI governance or assurance
  • Experience running scenario exercises

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Depends on a scenario

Superintelligent systems with major strategic capability

What AI would need to do
Systems substantially exceed human expert groups across broad consequential cognitive tasks.
What organisations would need to decide
Such systems are developed or deployed and institutions seek credible control and external oversight.
What would rule it out
No broad superhuman capability or no usable, governable deployment emerges.

We give no date. The role becomes real if both conditions hold.

Skills that matter

  • AI controlAdvancedLimit harm from potentially untrusted AI behaviour
  • Formal verificationAdvancedProve stated properties under explicit assumptions
  • AI governance and assuranceWorkingAssign accountability and verify lifecycle controls
  • Frontier scenario analysisWorkingExplore conditional outcomes without claiming predictions

Other roles in superintelligence control and containment assurance

ScenarioSuperintelligence Control Assurance ArchitectA Superintelligence Control Assurance Architect would judge whether claims of control over broadly superhuman systems hold up. It depends on how AI…ScenarioSuperintelligent System Containment ResearcherA containment researcher would test whether enforceable limits can hold against broadly superhuman AI. The role depends on how AI develops, and it…ScenarioSuperintelligence Strategic Risk AnalystA Superintelligence Strategic Risk Analyst would map how broadly superhuman systems could affect institutions and security. Whether the job exists…

Related roles in other families

ScenarioGeneral-Purpose Autonomy Assurance ArchitectGeneral-purpose autonomy assuranceA General-Purpose Autonomy Assurance Architect would design how an organisation gains justified confidence in systems given broad, consequential…ScenarioCross-Domain Capability Certification DesignerGeneral-purpose autonomy assuranceA Cross-Domain Capability Certification Designer would define what a general-purpose AI system can credibly be said to do across consequential…ScenarioAutonomous Delegation Accountability OfficerGeneral-purpose autonomy assuranceAn Autonomous Delegation Accountability Officer would keep track of who authorised what when AI systems carry out broad work. The role depends on…ScenarioGeneral-Purpose System Decommissioning PlannerGeneral-purpose autonomy assuranceA General-Purpose System Decommissioning Planner would prepare the controlled withdrawal of autonomous systems that run deeply inside an…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert. Scenario roles describe responsibilities that depend on stated conditions; they are not forecasts.

← Superintelligence control and containment assuranceAll new job families

Start a search

Hiring a Superintelligence Intervention Protocol Designer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.