Member of Technical Staff Cyberforensics
METR (Model Evaluation & Threat Research) is an independent nonprofit research organization that evaluates frontier AI systems’ autonomous capabilities and catastrophic-risk potential.
Funding history
Investors
About METR
METR develops scientific methods and runs empirical evaluations of frontier AI systems, including autonomous-task capability, evaluation-integrity behavior, and mitigations, to inform public and policy decision-making about AI risks.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will conduct embedded incident investigations and red-team agent-monitoring and security systems. Between exercises, you will develop methods and tooling, coordinate future exercises, write findings, and contribute to incident tracking and risk reports. You will build LLM-powered pipelines to triage transcripts, cluster behavior, and flag deception.
Requirements
- Digital forensics and incident response experience investigating severe security incidents end to end
- Experience with evidence acquisition and preservation
- Experience reconstructing logs and timelines across cloud, network, endpoint, and identity systems
- Attacker tradecraft analysis and post-incident reporting experience
- Cloud and infrastructure fluency across AWS, Kubernetes, containers, CI/CD, and package registries
- Understanding of frontier model training and deployment
- Experience building and analyzing with LLMs
- Ability to run rigorous investigations and write findings that withstand scrutiny
Responsibilities
- Conduct embedded incident investigations
- Red-team agent monitoring and security systems
- Develop investigation methodologies and tooling
- Write findings and contribute to incident tracking and risk reports
- Build LLM-powered forensic pipelines to triage transcripts, cluster behaviors, and flag deception