{"schemaVersion":"jobsearcher.job.v1","id":"5a0c2f2365f5bb420c64ab1c","url":"https://jobsearcher.com/jobs/5a0c2f2365f5bb420c64ab1c","canonicalUrl":"https://jobsearcher.com/jobs/5a0c2f2365f5bb420c64ab1c","title":"ML Performance Engineer – Multi-Node Training & Kernels","description":"Veeda AI in California is building the next generation of multimodal foundation world models for Physical AI. You will design and optimize distributed training and inference pipelines on large GPU clusters, focusing on low-latency, high-throughput workloads.\r\nThe role requires deep expertise in PyTorch, large-scale parallelism, and CUDA kernel work, with a track record of improving hardware utilization and stability at scale.#J-18808-Ljbffr","company":"Veeda Ai","rawCompany":"veeda ai","city":"Sacramento","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-14T02:11:37.862Z","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":"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"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"ML Performance Engineer – Multi-Node Training & Kernels","description":"Veeda AI in California is building the next generation of multimodal foundation world models for Physical AI. You will design and optimize distributed training and inference pipelines on large GPU clusters, focusing on low-latency, high-throughput workloads.\r\nThe role requires deep expertise in PyTorch, large-scale parallelism, and CUDA kernel work, with a track record of improving hardware utilization and stability at scale.#J-18808-Ljbffr","datePosted":"2026-10-14T02:11:37.862Z","dateModified":"2026-10-14T02:11:37.862Z","hiringOrganization":{"@type":"Organization","name":"Veeda Ai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Sacramento","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"5a0c2f2365f5bb420c64ab1c"},"url":"https://jobsearcher.com/jobs/5a0c2f2365f5bb420c64ab1c"}}