Member of Technical Staff Evaluation Execution
METR (Model Evaluation and Threat Research) is an independent research nonprofit that evaluates frontier AI systems’ capabilities and catastrophic-risk potential.
Funding history
Investors
About METR
METR develops scientific methods and conducts empirical evaluations of frontier AI systems, focusing on autonomous capabilities, AI-assisted R&D, evaluation-integrity threats, and mitigations. It publishes research and risk assessments to inform public and policy decision-making.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will run models on evaluation tasks, integrate them into agent scaffolds, inspect results, and improve evaluation software and infrastructure. You will communicate findings through graphs and written reports, coordinate sensitive evaluation work with stakeholders, and manage multiple concurrent evaluation projects.
Requirements
- Software engineering and infrastructure fundamentals
- Ability to debug unfamiliar systems from logs and fix performance bottlenecks
- Ability to work quickly and prioritize high-impact work
- High attention to detail
Responsibilities
- Run models on evaluation tasks and review results carefully
- Integrate models into agent scaffolds and evaluation infrastructure
- Build software that improves evaluation speed and informativeness
- Design graphs and communicate conclusions to varied audiences
- Manage concurrent evaluation projects and stakeholders
- Coordinate sensitive evaluations with leadership, lab contacts, and regulators