{"schemaVersion":"jobsearcher.job.v1","id":"0bcc8bf1c7a3e870df88e2b6","url":"https://jobsearcher.com/jobs/0bcc8bf1c7a3e870df88e2b6","canonicalUrl":"https://jobsearcher.com/jobs/0bcc8bf1c7a3e870df88e2b6","title":"Hybrid GPU AI Inference Engineer","description":"Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference on Intel GPUs. You will optimize the end-to-end stack, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization. You will upstream improvements to vLLM, SGLang, and PyTorch, collaborating with architecture and compiler teams to shape future GPU roadmaps. This role offers hybrid work and a competitive compensation package.\n#J-18808-Ljbffr","company":"Intel","rawCompany":"intel","city":"Eastern","state":"KY","isRemote":false,"isActive":false,"createdAt":"2026-10-14T04:14:38.580Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"17-2061.00","title":"Computer Hardware Engineers","slug":"computer-hardware-engineers"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"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":"Hybrid GPU AI Inference Engineer","description":"Intel Corporation is seeking a performance-obsessed AI Infrastructure Engineer to push LLM inference on Intel GPUs. You will optimize the end-to-end stack, profile bottlenecks, and write high-performance kernels for attention, MoE, and quantization. You will upstream improvements to vLLM, SGLang, and PyTorch, collaborating with architecture and compiler teams to shape future GPU roadmaps. This role offers hybrid work and a competitive compensation package.\n#J-18808-Ljbffr","datePosted":"2026-10-14T04:14:38.580Z","dateModified":"2026-10-14T04:14:38.580Z","hiringOrganization":{"@type":"Organization","name":"Intel","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Eastern","addressRegion":"KY","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0bcc8bf1c7a3e870df88e2b6"},"url":"https://jobsearcher.com/jobs/0bcc8bf1c7a3e870df88e2b6"}}