{"schemaVersion":"jobsearcher.job.v1","id":"6a9960bfcad584786ccb1db7","url":"https://jobsearcher.com/jobs/6a9960bfcad584786ccb1db7","canonicalUrl":"https://jobsearcher.com/jobs/6a9960bfcad584786ccb1db7","title":"Staff Engineer, Large-Scale GPU Pre-Training Systems","description":"Magic AI, Inc. is seeking a Member of Technical Staff for Pre-training Systems to design and operate distributed infrastructure that trains long-context models at scale.\nThe role focuses on large-scale model training across thousands of GPUs, ensuring performance, reliability, and reproducibility in extreme-scale environments. You will own systems handling memory pressure, cross-device communication, fault-tolerant jobs, and efficient sequence packing, collaborating with Kernels and Research to\n\n#J-18808-Ljbffr","company":"Magic Ai","rawCompany":"magic ai","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-08-03T03:29:09.773Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"518210","title":"Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services","slug":"computing-infrastructure-providers-data-processing-web-hosting-and-related-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Staff Engineer, Large-Scale GPU Pre-Training Systems","description":"Magic AI, Inc. is seeking a Member of Technical Staff for Pre-training Systems to design and operate distributed infrastructure that trains long-context models at scale.\nThe role focuses on large-scale model training across thousands of GPUs, ensuring performance, reliability, and reproducibility in extreme-scale environments. You will own systems handling memory pressure, cross-device communication, fault-tolerant jobs, and efficient sequence packing, collaborating with Kernels and Research to\n\n#J-18808-Ljbffr","datePosted":"2026-08-03T03:29:09.773Z","dateModified":"2026-08-03T03:29:09.773Z","hiringOrganization":{"@type":"Organization","name":"Magic Ai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"6a9960bfcad584786ccb1db7"},"url":"https://jobsearcher.com/jobs/6a9960bfcad584786ccb1db7"}}