{"schemaVersion":"jobsearcher.job.v1","id":"d3487cb65aa5144a83c87f74","url":"https://jobsearcher.com/jobs/d3487cb65aa5144a83c87f74","canonicalUrl":"https://jobsearcher.com/jobs/d3487cb65aa5144a83c87f74","title":"AI Benchmark Quality Engineer for Task Evaluation","description":"Obsidian is seeking a candid evaluator to assess the quality, correctness, and reproducibility of software-engineering benchmark tasks used to train frontier AI labs. You will review repository-level tasks, reference patches, test harnesses, and grading integrity, and provide rubric-based written feedback.\nResponsibilities include identifying gaps in tooling, ensuring task reproducibility across environments, and delivering concrete, rubric-based assessments to guide model training and\n\n#J-18808-Ljbffr","company":"Obsidian","rawCompany":"obsidian","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-09-09T03:41:46.620Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1253.00","title":"Software Quality Assurance Analysts and Testers","slug":"software-quality-assurance-analysts-and-testers"},{"code":"17-2112.02","title":"Validation Engineers","slug":"validation-engineers"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"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":"AI Benchmark Quality Engineer for Task Evaluation","description":"Obsidian is seeking a candid evaluator to assess the quality, correctness, and reproducibility of software-engineering benchmark tasks used to train frontier AI labs. You will review repository-level tasks, reference patches, test harnesses, and grading integrity, and provide rubric-based written feedback.\nResponsibilities include identifying gaps in tooling, ensuring task reproducibility across environments, and delivering concrete, rubric-based assessments to guide model training and\n\n#J-18808-Ljbffr","datePosted":"2026-09-09T03:41:46.620Z","dateModified":"2026-09-09T03:41:46.620Z","hiringOrganization":{"@type":"Organization","name":"Obsidian","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"d3487cb65aa5144a83c87f74"},"url":"https://jobsearcher.com/jobs/d3487cb65aa5144a83c87f74"}}