{"schemaVersion":"jobsearcher.job.v1","id":"e371ce0cd6e566df14ef8f3b","url":"https://jobsearcher.com/jobs/e371ce0cd6e566df14ef8f3b","canonicalUrl":"https://jobsearcher.com/jobs/e371ce0cd6e566df14ef8f3b","title":"Performance Kernel Engineer for High-Speed GPU Inference","description":"Inferact Inc. is seeking a Performance Engineer in San Francisco, California, focused on optimizing GPU performance for vLLM, the world's AI inference engine.\nThe ideal candidate will have deep experience in CUDA, a strong grasp of GPU architecture, and the ability to write high-performance code in C++ and Python. This role can be remote for exceptional candidates. The compensation range is $200,000 - $400,000 plus equity, with excellent health benefits.\n\n#J-18808-Ljbffr","company":"Inferact","rawCompany":"inferact","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-06-26T04:55:39.890Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"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"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"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":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Performance Kernel Engineer for High-Speed GPU Inference","description":"Inferact Inc. is seeking a Performance Engineer in San Francisco, California, focused on optimizing GPU performance for vLLM, the world's AI inference engine.\nThe ideal candidate will have deep experience in CUDA, a strong grasp of GPU architecture, and the ability to write high-performance code in C++ and Python. This role can be remote for exceptional candidates. The compensation range is $200,000 - $400,000 plus equity, with excellent health benefits.\n\n#J-18808-Ljbffr","datePosted":"2026-06-26T04:55:39.890Z","dateModified":"2026-06-26T04:55:39.890Z","hiringOrganization":{"@type":"Organization","name":"Inferact","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"e371ce0cd6e566df14ef8f3b"},"url":"https://jobsearcher.com/jobs/e371ce0cd6e566df14ef8f3b"}}