{"schemaVersion":"jobsearcher.job.v1","id":"5d77de9f4b2aabb1f7efdf46","url":"https://jobsearcher.com/jobs/5d77de9f4b2aabb1f7efdf46","canonicalUrl":"https://jobsearcher.com/jobs/5d77de9f4b2aabb1f7efdf46","title":"ML Infrastructure Engineer: Scale & Performance","description":"Physical Intelligence in San Francisco is building the core ML infrastructure to scale training from prototype to production-grade runs. The ML Infrastructure team owns training/inference systems, scheduling, checkpointing, and metrics collection.\r\nYou will scale JAX-based training across TPU and GPU clusters, profile memory usage, improve throughput, and create abstractions for launching and monitoring experiments in close collaboration with researchers.#J-18808-Ljbffr","company":"Physical Intelligence","rawCompany":"physical intelligence","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-09-23T01:14:13.859Z","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":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"ML Infrastructure Engineer: Scale & Performance","description":"Physical Intelligence in San Francisco is building the core ML infrastructure to scale training from prototype to production-grade runs. The ML Infrastructure team owns training/inference systems, scheduling, checkpointing, and metrics collection.\r\nYou will scale JAX-based training across TPU and GPU clusters, profile memory usage, improve throughput, and create abstractions for launching and monitoring experiments in close collaboration with researchers.#J-18808-Ljbffr","datePosted":"2026-09-23T01:14:13.859Z","dateModified":"2026-09-23T01:14:13.859Z","hiringOrganization":{"@type":"Organization","name":"Physical Intelligence","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"5d77de9f4b2aabb1f7efdf46"},"url":"https://jobsearcher.com/jobs/5d77de9f4b2aabb1f7efdf46"}}