Technical Policy Researcher

About Irregular
Irregular is the first frontier security lab with the mission of protecting the world in the time of increasingly capable and sophisticated AI systems. We build next-generation defenses through high-fidelity research platforms that simulate and monitor real-world AI security scenarios.

As AI systems become more powerful, we focus on staying ahead of emerging threats and vulnerabilities, ensuring these transformative technologies can be deployed safely and securely.

About the Role
As a Technical Policy researcher at Irregular, you'll tackle some of the biggest and most complex questions of AI development and deployment. Your work outlining problems, solutions and principles for governments, frontier labs, and deployers will shape the emerging field of AI security.

Representative projects:

• Threat modeling and fleshing out in what specific way could a strong cyber-capable model cause harm.
• Taxonomies for dangerous AI capabilities or mitigations.
• Policy proposals for models' refusal policy (which prompts models should refuse to follow).
• Following up on publications and news on AI policy, AI risks and mitigations, and technical AI research.
• Writing academic papers and blog posts detailing our research around evaluation theory or mitigation recommendations.
• Publishing your research and/or delivering research to our customers.

You may be a good fit if you have

• Strong research skills in both quantitative and qualitative methods.
• Strong writing skills, and experience as an academic (or industry equivalent) writer or analyst.
• Interest in AI and specifically AI security.
• Technical proficiency.
• Background in AI/cybersecurity - a big advantage