Want to know if this job is worth applying to?
Berkeley, Missouri, United States
Hybrid
Available
We are a nonprofit research organization that develops scientific methods to assess AI capabilities, risks, and mitigations, with a specific focus on threats related to AI R&D automation and misalignment.
We believe it is robustly good for policymakers and civil society to have a clear understanding of risks from AI systems, and we are extremely excited to build a team of ambitious, excellent people to tackle one of the most important challenges of our time.
Security at METR is becoming its own dedicated team, and you will lead it. It is extremely important that we continue to be an organization that frontier AI labs, governments, and the public trust with sensitive model access and confidential information. As misalignment incidents become more extreme and confidential information about models and frontier AI labs becomes more valuable, we expect to be under increasingly heavy pressure from external actors and internal agents.
We now need someone thinking about organizational security posture full time and proactively planning against future threats. You will own security at METR, ensuring our security strategy grows as the organization does.
Advising METR leadership: You will advise on the security implications of new partnerships, evaluation programs, and model access arrangements before commitments are made.
Setting organizational strategy: You will set our security roadmap and build up our security culture, consolidating ownership of security areas that today are spread across teams and filling gaps that currently have no owner.
Managing the security team: You will manage a team of security engineers and contractors across incident response, infrastructure hardening, red-teaming, and meeting the security requirements of our external partnerships.
Deep security and management background. You’ve been accountable for an org’s security posture or led high-stakes security engagements in the past, including being part of or leading an IR team.
Hands-on mentality. You’re still interested in the lower-level security details, and can personally investigate an incident, read a cloud IAM policy, review a sandboxing design, or configure identity and endpoint tooling.
Threat modeling and red teaming experience. You can reason about defending against both insiders and sophisticated, well-resourced adversaries.
Mission-aligned. You care deeply about METR’s mission of investigating catastrophic risks for AI.
Built a security team from scratch (first security hire or founding CISO).
Led incident response end to end, including decision-making and communication to stakeholders.
Experience securing AI/ML systems or agent infrastructure.
Familiarity with the tooling in our environment: DataDog, Kubernetes, CrowdStrike Falcon, Okta, Tailscale, Pulumi, PostgreSQL.
