{"schemaVersion":"jobsearcher.job.v1","id":"717e658aabeb341892ae84c3","url":"https://jobsearcher.com/jobs/717e658aabeb341892ae84c3","canonicalUrl":"https://jobsearcher.com/jobs/717e658aabeb341892ae84c3","title":"LLM Inference Optimization Engineer","description":"GMI Cloud, a fast-growing AI infrastructure company, is hiring a Machine Learning Engineer, LLM Optimization to build a world-leading inference optimization team. You will drive research, validation, and productionization of advanced optimization techniques to boost latency, throughput, and cost efficiency across the inference platform.\nYou will focus on B200-first optimization with H200 evolution, collaborating with platform and infra teams to turn new ideas into measurable customer-ready\n\n#J-18808-Ljbffr","company":"Gmi Cloud","rawCompany":"gmi cloud","city":"Mountain View","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-08-31T03:10:11.630Z","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":"LLM Inference Optimization Engineer","description":"GMI Cloud, a fast-growing AI infrastructure company, is hiring a Machine Learning Engineer, LLM Optimization to build a world-leading inference optimization team. You will drive research, validation, and productionization of advanced optimization techniques to boost latency, throughput, and cost efficiency across the inference platform.\nYou will focus on B200-first optimization with H200 evolution, collaborating with platform and infra teams to turn new ideas into measurable customer-ready\n\n#J-18808-Ljbffr","datePosted":"2026-08-31T03:10:11.630Z","dateModified":"2026-08-31T03:10:11.630Z","hiringOrganization":{"@type":"Organization","name":"Gmi Cloud","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mountain View","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"717e658aabeb341892ae84c3"},"url":"https://jobsearcher.com/jobs/717e658aabeb341892ae84c3"}}