{"schemaVersion":"jobsearcher.job.v1","id":"d7704895dfa05dcb5d465f77","url":"https://jobsearcher.com/jobs/d7704895dfa05dcb5d465f77","canonicalUrl":"https://jobsearcher.com/jobs/d7704895dfa05dcb5d465f77","title":"Machine Learning Engineer - Model Evaluation & Experimentation","description":"Machine Learning Engineer/ResearcherJoin a pioneering AI initiative focused on building the next generation of evaluation benchmarks for frontier AI models. We are seeking experienced Machine Learning Engineers and Researchers to bring hands-on expertise in model development, experimentation, and evaluation to create rigorous benchmark tasks for advanced AI systems.In this role, you will design sophisticated, multi-step machine learning challenges inspired by real-world research workflows. From implementing experimental ideas and running training pipelines to analyzing model behavior and validating results, you will help establish high-quality evaluation benchmarks that reveal the strengths and limitations of frontier AI models.This is a fully remote, full-time engagement requiring approximately 35 hours per week.","company":"Weekday","rawCompany":"weekday","city":"Denver","state":"CO","isRemote":false,"isActive":false,"createdAt":"2026-10-15T12:57:02.213Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Machine Learning Engineer - Model Evaluation & Experimentation","description":"Machine Learning Engineer/ResearcherJoin a pioneering AI initiative focused on building the next generation of evaluation benchmarks for frontier AI models. We are seeking experienced Machine Learning Engineers and Researchers to bring hands-on expertise in model development, experimentation, and evaluation to create rigorous benchmark tasks for advanced AI systems.In this role, you will design sophisticated, multi-step machine learning challenges inspired by real-world research workflows. From implementing experimental ideas and running training pipelines to analyzing model behavior and validating results, you will help establish high-quality evaluation benchmarks that reveal the strengths and limitations of frontier AI models.This is a fully remote, full-time engagement requiring approximately 35 hours per week.","datePosted":"2026-10-15T12:57:02.213Z","dateModified":"2026-10-15T12:57:02.213Z","hiringOrganization":{"@type":"Organization","name":"Weekday","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Denver","addressRegion":"CO","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"d7704895dfa05dcb5d465f77"},"url":"https://jobsearcher.com/jobs/d7704895dfa05dcb5d465f77"}}