
11 - 50 employees
Founded 2022
π€ Artificial Intelligence
βοΈ SaaS
Artificial Intelligence β’ Research β’ SaaS
METR is a research organization focused on evaluating and understanding the capabilities and risks of frontier AI systems. They develop and run tests to measure AI performance, particularly in autonomous capabilities and AI R&D. By collaborating with leading AI companies like Anthropic and OpenAI, METR aims to enhance third-party evaluations to manage the emerging risks of advanced AI technologies comprehensively.
π August 6
π Anywhere in the World
π΅ $150 - $300 / hour
β³ Contract/Temporary
π Senior
π·π»ββοΈ Engineer
π» Ghost score 34%
Where this job comes from
Posted on METR's careers page β, not through a job board
First seen by Remote Rocketship August 6
Still open on METR's site. Checked 3 hours ago.

11 - 50 employees
Founded 2022
π€ Artificial Intelligence
βοΈ SaaS
Artificial Intelligence β’ Research β’ SaaS
METR is a research organization focused on evaluating and understanding the capabilities and risks of frontier AI systems. They develop and run tests to measure AI performance, particularly in autonomous capabilities and AI R&D. By collaborating with leading AI companies like Anthropic and OpenAI, METR aims to enhance third-party evaluations to manage the emerging risks of advanced AI technologies comprehensively.
β’ Develop difficult, novel tasks for AI models that remain challenging as model time horizons grow β’ Perform quality assurance for existing tasks, verifying solvability and that models receive only the necessary information β’ Baseline tasks within areas of expertise when helpful β’ Score task completions from AIs or human baseliners β’ Improve task development infrastructure and workflows β’ Contribute to evaluations of frontier AI systems supporting METRβs Time Horizons methodology
β’ Several years of experience working on complex software engineering projects and codebases β’ Experience building hard, ideally agent-based, AI evaluations β’ Experience with evaluations such as RE-Bench, HCAST, SWE-bench Verified, Cybench, or GPQA β’ Ideally experience using the Inspect framework β’ High attention to detail, including spotting misspecifications and ambiguity β’ Familiarity with METR infrastructure, including Hawk, is a plus β’ Familiarity with the methodology behind METRβs Time Horizons work is a plus β’ Availability for 20β40 hours per week β’ Minimum of 1 hour of overlap with the Pacific Coast Time workday
β’ Flexible schedule determined by you β’ Remote work worldwide β’ Flexible working hours of 20β40 hours per week β’ Individuals who contribute >80 hours will be acknowledged in the final research output (if desired)
Apply NowImprove your chances of getting an interview by checking your resume score before you apply.
π June 26
Forward Deployed Engineer at Vozy deploying and optimizing AI voice agents for customer resolutions. Collaborate with clients and manage AI integrations in a dynamic environment.
π Anywhere in the World
π° $1M Debt Financing on 2022-10
β³ Contract/Temporary
π‘ Mid-level
π Senior
π·π»ββοΈ Engineer
π£οΈπͺπΈ Spanish Required