{"schemaVersion":"jobsearcher.job.v1","id":"59065624f5c744dc02fd18d4","url":"https://jobsearcher.com/jobs/59065624f5c744dc02fd18d4","canonicalUrl":"https://jobsearcher.com/jobs/59065624f5c744dc02fd18d4","title":"Principal GPU Inference & Workload Optimizer","description":"Horizon AI is seeking a Principal Inference & Workload Optimization Lead to own how customer AI workloads run on committed capacity and to build autonomous optimization that scales beyond a single expert.\nYou will profile workloads, establish baselines on current NVIDIA hardware, develop agent-executable improvements, and partner with customer and internal teams to optimize GPU allocation and routing. This role emphasizes measurable performance and scalable impact across clusters.\n\n#J-18808-Ljbffr","company":"Stn","rawCompany":"stn","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-27T03:38:23.761Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"11-3021.00","title":"Computer and Information Systems Managers","slug":"computer-and-information-systems-managers"},{"code":"15-1299.00","title":"Computer Occupations, All Other","slug":"computer-occupations-all-other"}],"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":"334111","title":"Electronic Computer Manufacturing","slug":"electronic-computer-manufacturing"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Principal GPU Inference & Workload Optimizer","description":"Horizon AI is seeking a Principal Inference & Workload Optimization Lead to own how customer AI workloads run on committed capacity and to build autonomous optimization that scales beyond a single expert.\nYou will profile workloads, establish baselines on current NVIDIA hardware, develop agent-executable improvements, and partner with customer and internal teams to optimize GPU allocation and routing. This role emphasizes measurable performance and scalable impact across clusters.\n\n#J-18808-Ljbffr","datePosted":"2026-10-27T03:38:23.761Z","dateModified":"2026-10-27T03:38:23.761Z","hiringOrganization":{"@type":"Organization","name":"Stn","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"59065624f5c744dc02fd18d4"},"url":"https://jobsearcher.com/jobs/59065624f5c744dc02fd18d4"}}