{"schemaVersion":"jobsearcher.job.v1","id":"57c249728902f3e6bd71af49","url":"https://jobsearcher.com/jobs/57c249728902f3e6bd71af49","canonicalUrl":"https://jobsearcher.com/jobs/57c249728902f3e6bd71af49","title":"Inference Runtime Performance Engineer — GPU Kernels","description":"iFrame Corporation is hiring for a role on the runtime team to own end-to-end performance for multiple model families on our managed inference runtime. You will write fused CUDA/Triton kernels and work across tokenizer through KV cache and decoding, targeting H100/H200 and other accelerators. With 5+ years in systems-level performance and a track record of speed-ups, you will design long-context primitives and publish external write-ups quarterly while sharing on-call duties with SRE and #J-18808-Ljbffr","company":"Iframe","rawCompany":"iframe","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-09-06T12:03:40.233Z","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":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"518210","title":"Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services","slug":"computing-infrastructure-providers-data-processing-web-hosting-and-related-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Inference Runtime Performance Engineer — GPU Kernels","description":"iFrame Corporation is hiring for a role on the runtime team to own end-to-end performance for multiple model families on our managed inference runtime. You will write fused CUDA/Triton kernels and work across tokenizer through KV cache and decoding, targeting H100/H200 and other accelerators. With 5+ years in systems-level performance and a track record of speed-ups, you will design long-context primitives and publish external write-ups quarterly while sharing on-call duties with SRE and #J-18808-Ljbffr","datePosted":"2026-09-06T12:03:40.233Z","dateModified":"2026-09-06T12:03:40.233Z","hiringOrganization":{"@type":"Organization","name":"Iframe","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"57c249728902f3e6bd71af49"},"url":"https://jobsearcher.com/jobs/57c249728902f3e6bd71af49"}}