Security Research Engineer
Confirmed on the employer's own hiring board on Oct 10, 2026. First seen by Alion on Aug 27, 2026.
About AVERI:
The AI Verification and Evaluation Research Institute (AVERI) is a US-based nonprofit with the mission to make third-party auditing of frontier AI effective and universal. AVERI aims to bring about a world in which the most powerful AI systems - and the companies that build them - are rigorously audited for safety and security by third parties. We believe this independent auditing layer is essential for enabling confident deployment of AI and managing critical risks from this increasingly powerful technology.
About the Role:
AVERI is looking for a Security Research Engineer to lead and execute on cyber risk strategy. This role reports to Sean McGregor and would involve a mix of ensuring the security of AVERI’s pilots, informing secure practices across the frontier audit ecosystem, and contributing cybersecurity risk expertise on pilots. Given AVERI’s early stage (launched in January ‘26), early staff are expected to take on a wide range of responsibilities, many of which will eventually be transitioned to more specialized personnel.
What You’ll Do:
Design new processes and technologies for more effective and scalable future audits as identified by pilot audits.
Build systems enabling efficient, secure audits, including novel privacy-enhancing technologies (PETs) combining deep auditor access to non-public information at AI companies with strong protection of that information.
Inform and support the evaluation of cybersecurity risks related to frontier AI, including cybersecurity organizational practices, system defenses, system guardrails, and other elements related to vulnerability and risk.
Develop and deploy code and data as direct instruments for advancing safety, rather than managing them as abstract concepts in policy documents.
Strengthen AVERI's internal IT infrastructure and cybersecurity posture, covering areas like access controls, data protection, device management, and incident response readiness.
About You:
Experience building systems that have shipped to production environments.
Demonstrated ability to build novel systems and confidence that you could learn how to build anything with enough time and effort.
Familiar with language model safety and security research and practice.
Effective communicator to cybersecurity and non-technical colleagues about concepts related to threat models, cryptography, best practices, and risk.
High integrity and discretion.
What We Offer:
This is a full-time remote position which will require travel at approximately once per quarter and possibly significantly more, especially to Washington, DC and San Francisco
Salary range: $220,000-$330,000 USD
Comprehensive medical benefits, including generous reimbursement of eligible HRA expenses
6% unrestricted retirement contribution
Unlimited PTO
A work enablement and professional development package of up to $22,200 per year
A mission-driven team committed to integrity and purpose, providing a supportive environment with meaningful opportunities for career growth
If you think you are perfect for this role, but you do not meet all of the requirements, we strongly encourage you to apply and tell us why you’d be a great fit. We are committed to fostering a diverse and inclusive environment where all employees have the opportunity to succeed. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, or any other legally protected status. Please let us know what accommodations you might need when applying or if asked to be interviewed by emailing us at [email protected]