{"schemaVersion":"jobsearcher.job.v1","id":"1ccc8efbbddc2993adf77a33","url":"https://jobsearcher.com/jobs/1ccc8efbbddc2993adf77a33","canonicalUrl":"https://jobsearcher.com/jobs/1ccc8efbbddc2993adf77a33","title":"Research Engineer, Benchmarking","description":"# Research Engineer, BenchmarkingEngineeringSan FranciscoFull-timeBuild the benchmarks frontier labs use to measure real-world coding and computer-use capability. Translate expert workflows into rigorous, verifiable evaluations, run them against frontier models, and publish numbers that hold up under adversarial scrutiny.Across every role at Refresh: you're willing to ship full-stack work on our core stack (Vercel, Supabase, Render) when it's needed, and you're comfortable with reinforcement learning and supervised fine-tuning at a high level.\n#J-18808-Ljbffr","company":"Refresh Ai","rawCompany":"refresh ai","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-06-17T03:44:03.202Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"}],"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":"Research Engineer, Benchmarking","description":"# Research Engineer, BenchmarkingEngineeringSan FranciscoFull-timeBuild the benchmarks frontier labs use to measure real-world coding and computer-use capability. Translate expert workflows into rigorous, verifiable evaluations, run them against frontier models, and publish numbers that hold up under adversarial scrutiny.Across every role at Refresh: you're willing to ship full-stack work on our core stack (Vercel, Supabase, Render) when it's needed, and you're comfortable with reinforcement learning and supervised fine-tuning at a high level.\n#J-18808-Ljbffr","datePosted":"2026-06-17T03:44:03.202Z","dateModified":"2026-06-17T03:44:03.202Z","hiringOrganization":{"@type":"Organization","name":"Refresh Ai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"1ccc8efbbddc2993adf77a33"},"url":"https://jobsearcher.com/jobs/1ccc8efbbddc2993adf77a33"}}