{"schemaVersion":"jobsearcher.job.v1","id":"6bd60b4ba516a728ce9e27be","url":"https://jobsearcher.com/jobs/6bd60b4ba516a728ce9e27be","canonicalUrl":"https://jobsearcher.com/jobs/6bd60b4ba516a728ce9e27be","title":"Real-Time GPU Optimization Engineer - Inference","description":"techire ai is seeking a GPU Optimisation Engineer for real-time inference in production AI workloads. The role focuses on pushing GPU performance to sub-50ms latency under high concurrency, close to the metal across kernel and runtime layers.\nYou will profile and optimize large generative models, write custom CUDA/Triton kernels, and collaborate with research to deliver production-ready inference at scale. SF relocation/visa sponsorship available.\n\n#J-18808-Ljbffr","company":"Techire Ai","rawCompany":"techire ai","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-09-11T04:55:41.653Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"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":"Real-Time GPU Optimization Engineer - Inference","description":"techire ai is seeking a GPU Optimisation Engineer for real-time inference in production AI workloads. The role focuses on pushing GPU performance to sub-50ms latency under high concurrency, close to the metal across kernel and runtime layers.\nYou will profile and optimize large generative models, write custom CUDA/Triton kernels, and collaborate with research to deliver production-ready inference at scale. SF relocation/visa sponsorship available.\n\n#J-18808-Ljbffr","datePosted":"2026-09-11T04:55:41.653Z","dateModified":"2026-09-11T04:55:41.653Z","hiringOrganization":{"@type":"Organization","name":"Techire Ai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"6bd60b4ba516a728ce9e27be"},"url":"https://jobsearcher.com/jobs/6bd60b4ba516a728ce9e27be"}}