Senior Advisor, Advanced Guardrails for AI-Induced Incidents

Institute for Security and Technology; Washington (District of Columbia); On-site; USD 90,000 - 100,000; Part time

Job summary

The Institute for Security and Technology seeks a Senior Advisor, Advanced Guardrails for AI-Induced Incidents to provide strategic and technical guidance on advanced AI risks and safeguards. You will lead research on loss-of-control scenarios, evaluate prevent/detect/mitigate approaches, and translate findings into practical guidance for policy and practice.

As an independent contractor, you will engage researchers, AI developers, and government stakeholders, convene workshops, and contribute

Qualifications

• Advanced degree (MS/PhD) in Computer Science, Machine Learning, AI Safety, or a related technical field.
• At least five years of experience with red teaming, threat modeling, or technical AI governance.
• Familiarity with AI loss-of-control research, AI control, model evaluations, agent security, containment, monitoring, or related safeguards.
• Track record of convening multidisciplinary experts on emerging or poorly understood risks, and producing technical or policy research.
• Demonstrated experience developing response frameworks, escalation processes, or scenario-based exercises (tabletops, simulations) for high-consequence situations.
• Ability to translate technical risk into practical operational guidance for mixed technical/policy audiences.
• Strong analytical, writing, and facilitation skills, with experience engaging stakeholders across government and industry

Responsibilities

• Provide strategic and technical guidance on IST’s work related to advanced AI risks, safeguards, and incident prevention.
• Lead and contribute to research on emerging AI capabilities, risks, and potential loss-of-control scenarios.
• Assess technical and institutional approaches for preventing, detecting, and mitigating high-consequence AI incidents.
• Identify emerging gaps in existing safeguards and areas where additional technical or governance measures may be needed.
• Engage with researchers, AI developers, government stakeholders, and other experts working on advanced AI safety and security.
• Convene and support expert discussions, workshops, and structured analytical exercises.
• Translate technical research and emerging evidence into actionable recommendations for policy and practice.
• Contribute to IST publications, briefings, and external engagements on AI risk reduction and preparedness.

Skills

Red teaming

Threat modeling

AI governance

Stakeholder engagement

Tabletop exercises

Education

MS/PhD in Computer Science, ML, AI Safety

Job description

Senior Advisor, Advanced Guardrails for AI-Induced Incidents/Contract

The Institute for Security and Technology (IST), a 501(c)(3) critical action think tank that unites technology and policy leaders to create solutions to emerging security challenges, is seeking an independent contractor for a Senior Advisor, Advanced Guardrails for AI-Induced Incidents to provide technical and strategic advice for IST’s work on AI loss of control (LOC) contingency planning, advanced safeguards, and preparedness for high-consequence AI incidents.

As increasingly capable AI systems gain greater autonomy and access to tools, infrastructure, and other real-world resources, existing safety and security mechanisms may be insufficient to prevent or contain emerging incidents. IST is developing a focused body of work to better understand the conditions that could precede loss of control, identify opportunities for intervention, and strengthen the technical and institutional mechanisms available to respond.

The Senior Advisor will lead a focused, time-bound effort bringing together research, adversarial analysis, stakeholder engagement, and technical and governance expertise to advance practical approaches for preventing and mitigating AI LOC.

Key Responsibilities

• Provide strategic and technical guidance on IST’s work related to advanced AI risks, safeguards, and incident prevention.


• Lead and contribute to research on emerging AI capabilities, risks, and potential loss-of-control scenarios.


• Assess technical and institutional approaches for preventing, detecting, and mitigating high-consequence AI incidents.


• Identify emerging gaps in existing safeguards and areas where additional technical or governance measures may be needed.


• Engage with researchers, AI developers, government stakeholders, and other experts working on advanced AI safety and security.


• Convene and support expert discussions, workshops, and structured analytical exercises.


• Translate technical research and emerging evidence into actionable recommendations for policy and practice.


• Contribute to IST publications, briefings, and external engagements on AI risk reduction and preparedness.

Qualifications/Requirements

• Advanced degree (MS/PhD) in Computer Science, Machine Learning, AI Safety, or a related technical field


• At least five years of experience with red teaming, threat modeling, or technical AI governance


• Familiarity with AI loss-of-control research, AI control, model evaluations, agent security, containment, monitoring, or related safeguards


• Track record of convening multidisciplinary experts on emerging or poorly understood risks, and producing technical or policy research


• Demonstrated experience developing response frameworks, escalation processes, or scenario-based exercises (tabletops, simulations) for high-consequence situations


• Ability to translate technical risk into practical operational guidance for mixed technical/policy audiences


• Strong analytical, writing, and facilitation skills, with experience engaging stakeholders across government and industry

Preferred

• Prior engagement with frontier AI labs or independent evaluation organizations


• Publications or demonstrated work in AI security and capability evaluation


• Familiarity with policy processes and government AI evaluation bodies

Compensation

This is an independent contractor engagement, estimated at 20 hours a week for a 12-month term (target: October 10, 2026 – October 10, 2027), to be confirmed based on actual start date).

We anticipate a contract value of up to $100,000 for the term, based on an estimated 20 hours per week; the final contract rate will be negotiated directly with the contractor

As an independent contractor, this role is not eligible