{"schemaVersion":"jobsearcher.job.v1","id":"404f8df1b929b3dd646eb7a8","url":"https://jobsearcher.com/jobs/404f8df1b929b3dd646eb7a8","canonicalUrl":"https://jobsearcher.com/jobs/404f8df1b929b3dd646eb7a8","title":"LLM Inference Intern: GPU, KV Cache & SoC","description":"Samsung Semiconductor in San Jose, CA, is offering a summer internship to work on cutting-edge SoC storage and memory projects. You will deploy and operate an LLM inference service on a multi-GPU server and build a reproducible benchmark harness to measure latency and throughput.\nThe role requires hands-on experience with Python and PyTorch on NVIDIA GPUs under Linux and familiarity with vLLM, SGLang, or Hugging Face TGI.\n\n#J-18808-Ljbffr","company":"Linuxconfig","rawCompany":"linuxconfig","city":"Folsom","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-11-14T04:25:44.630Z","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":"17-2061.00","title":"Computer Hardware Engineers","slug":"computer-hardware-engineers"}],"industries":[{"code":"334413","title":"Semiconductor and Related Device Manufacturing","slug":"semiconductor-and-related-device-manufacturing"},{"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"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"LLM Inference Intern: GPU, KV Cache & SoC","description":"Samsung Semiconductor in San Jose, CA, is offering a summer internship to work on cutting-edge SoC storage and memory projects. You will deploy and operate an LLM inference service on a multi-GPU server and build a reproducible benchmark harness to measure latency and throughput.\nThe role requires hands-on experience with Python and PyTorch on NVIDIA GPUs under Linux and familiarity with vLLM, SGLang, or Hugging Face TGI.\n\n#J-18808-Ljbffr","datePosted":"2026-11-14T04:25:44.630Z","dateModified":"2026-11-14T04:25:44.630Z","hiringOrganization":{"@type":"Organization","name":"Linuxconfig","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Folsom","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"404f8df1b929b3dd646eb7a8"},"url":"https://jobsearcher.com/jobs/404f8df1b929b3dd646eb7a8"}}