{"schemaVersion":"jobsearcher.job.v1","id":"56909dfb88b73a04604623f1","url":"https://jobsearcher.com/jobs/56909dfb88b73a04604623f1","canonicalUrl":"https://jobsearcher.com/jobs/56909dfb88b73a04604623f1","title":"GPU-Optimized LLM Inference Engineer","description":"Intel Corporation in the United States (US) seeks an experienced AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will work end-to-end across profiling, kernel development, and upstreaming optimizations into vLLM, SGLang, and PyTorch, influencing hardware and software co-design.\r\nResponsibilities include diagnosing bottlenecks, developing high-performance kernels for attention and MoE, and collaborating with architecture and compiler teams to plan#J-18808-Ljbffr","company":"Intel","rawCompany":"intel","city":"Austin","state":"TX","isRemote":false,"isActive":true,"createdAt":"2026-10-15T01:33:18.288Z","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":"334111","title":"Electronic Computer Manufacturing","slug":"electronic-computer-manufacturing"},{"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":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"GPU-Optimized LLM Inference Engineer","description":"Intel Corporation in the United States (US) seeks an experienced AI Infrastructure Engineer to push LLM inference on Intel GPUs to new performance heights. You will work end-to-end across profiling, kernel development, and upstreaming optimizations into vLLM, SGLang, and PyTorch, influencing hardware and software co-design.\r\nResponsibilities include diagnosing bottlenecks, developing high-performance kernels for attention and MoE, and collaborating with architecture and compiler teams to plan#J-18808-Ljbffr","datePosted":"2026-10-15T01:33:18.288Z","dateModified":"2026-10-15T01:33:18.288Z","hiringOrganization":{"@type":"Organization","name":"Intel","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Austin","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"56909dfb88b73a04604623f1"},"url":"https://jobsearcher.com/jobs/56909dfb88b73a04604623f1"}}