{"schemaVersion":"jobsearcher.job.v1","id":"eaff2347cdc5fc15a4e2c98e","url":"https://jobsearcher.com/jobs/eaff2347cdc5fc15a4e2c98e","canonicalUrl":"https://jobsearcher.com/jobs/eaff2347cdc5fc15a4e2c98e","title":"Distributed Production Inference Engineer","description":"Thinking Machines Lab Inc. is hiring a Software Engineer to design, build, and scale distributed production inference systems for Inkling, Inkling-Small, and Tinker.\r\nYou will own the end-to-end serving stack, from request routing to multi-node coordination and GPU utilization at scale. The role emphasizes production-first systems work, latency optimization, and deep observability, collaborating with research and infrastructure teams to translate evolving model architectures into reliable#J-18808-Ljbffr","company":"Thinking Machines Lab","rawCompany":"thinking machines lab","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-14T02:07:56.475Z","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":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Distributed Production Inference Engineer","description":"Thinking Machines Lab Inc. is hiring a Software Engineer to design, build, and scale distributed production inference systems for Inkling, Inkling-Small, and Tinker.\r\nYou will own the end-to-end serving stack, from request routing to multi-node coordination and GPU utilization at scale. The role emphasizes production-first systems work, latency optimization, and deep observability, collaborating with research and infrastructure teams to translate evolving model architectures into reliable#J-18808-Ljbffr","datePosted":"2026-10-14T02:07:56.475Z","dateModified":"2026-10-14T02:07:56.475Z","hiringOrganization":{"@type":"Organization","name":"Thinking Machines Lab","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"eaff2347cdc5fc15a4e2c98e"},"url":"https://jobsearcher.com/jobs/eaff2347cdc5fc15a4e2c98e"}}