{"schemaVersion":"jobsearcher.job.v1","id":"8f7cd3f67f70a15b738e52bc","url":"https://jobsearcher.com/jobs/8f7cd3f67f70a15b738e52bc","canonicalUrl":"https://jobsearcher.com/jobs/8f7cd3f67f70a15b738e52bc","title":"LLM Inference Optimization Engineer - Frontier Performance","description":"GMI Cloud, Inc is hiring world-class Machine Learning Engineers to advance LLM inference optimization leveraging GPUs and cutting-edge techniques. You will drive research, validation, and productionization of optimization strategies across NV platforms, with a focus on speed, efficiency, and scalability. You will collaborate with platform and infrastructure teams, contribute to open-source projects, and help define recipes and benchmarks for industry-leading inference performance.\n#J-18808-Ljbffr","company":"Gmi Cloud","rawCompany":"gmi cloud","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-03T03:27:49.335Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"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"}],"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":"LLM Inference Optimization Engineer - Frontier Performance","description":"GMI Cloud, Inc is hiring world-class Machine Learning Engineers to advance LLM inference optimization leveraging GPUs and cutting-edge techniques. You will drive research, validation, and productionization of optimization strategies across NV platforms, with a focus on speed, efficiency, and scalability. You will collaborate with platform and infrastructure teams, contribute to open-source projects, and help define recipes and benchmarks for industry-leading inference performance.\n#J-18808-Ljbffr","datePosted":"2026-10-03T03:27:49.335Z","dateModified":"2026-10-03T03:27:49.335Z","hiringOrganization":{"@type":"Organization","name":"Gmi Cloud","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"8f7cd3f67f70a15b738e52bc"},"url":"https://jobsearcher.com/jobs/8f7cd3f67f70a15b738e52bc"}}