{"schemaVersion":"jobsearcher.job.v1","id":"261b7db361f0f9b2df278418","url":"https://jobsearcher.com/jobs/261b7db361f0f9b2df278418","canonicalUrl":"https://jobsearcher.com/jobs/261b7db361f0f9b2df278418","title":"ML Systems Engineer — GPU & Distributed Inference","description":"The company is seeking an experienced ML systems engineer to optimize training and inference workloads for image, video, diffusion, and world-model tasks at their Menlo Park, CA site. You will profile bottlenecks, implement low-level GPU optimizations with CUDA and Triton, and help design distributed engines for diffusion models.\r\nThis role requires 2+ years in ML systems, strong CS fundamentals, and hands-on experience with PyTorch, Nsight, NCCL, and RDMA.#J-18808-Ljbffr","company":"True","rawCompany":"true","city":"Menlo Park","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-11-04T02:44:52.485Z","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":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"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"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"ML Systems Engineer — GPU & Distributed Inference","description":"The company is seeking an experienced ML systems engineer to optimize training and inference workloads for image, video, diffusion, and world-model tasks at their Menlo Park, CA site. You will profile bottlenecks, implement low-level GPU optimizations with CUDA and Triton, and help design distributed engines for diffusion models.\r\nThis role requires 2+ years in ML systems, strong CS fundamentals, and hands-on experience with PyTorch, Nsight, NCCL, and RDMA.#J-18808-Ljbffr","datePosted":"2026-11-04T02:44:52.485Z","dateModified":"2026-11-04T02:44:52.485Z","hiringOrganization":{"@type":"Organization","name":"True","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Menlo Park","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"261b7db361f0f9b2df278418"},"url":"https://jobsearcher.com/jobs/261b7db361f0f9b2df278418"}}