Security Research Engineer
US-based 501(c)(3) nonprofit advancing independent third-party auditing of frontier AI systems.
About AI Verification and Evaluation Research Institute (AVERI)
AVERI conducts frontier-AI audit pilots and technical and policy research, translating findings into open-source tools, auditing standards, and advocacy intended to make independent AI auditing effective and widely adopted.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design processes and technologies for scalable audits and build secure systems for auditing sensitive information. You will support cybersecurity-risk evaluations for frontier AI, develop and deploy code and data for safety work, and strengthen IT security through access controls, data protection, device management, and incident-response readiness. You will travel as required.
Requirements
- Experience building systems shipped to production environments
- Ability to build novel systems
- Familiarity with language-model safety and security research and practice
- Ability to communicate threat models, cryptography, best practices, and risk to technical and non-technical colleagues
- Integrity and discretion
Responsibilities
- Design processes and technologies for scalable future audits
- Build secure audit systems and privacy-enhancing technologies
- Support evaluations of cybersecurity risks related to frontier AI
- Develop and deploy code and data to advance safety
- Strengthen IT infrastructure and cybersecurity posture, including access controls, data protection, device management, and incident-response readiness
Benefits
- Comprehensive medical benefits with reimbursement of eligible HRA expenses
- 6% unrestricted retirement contribution
- Unlimited PTO
- Work enablement and professional development package up to $22,200 per year