{"schemaVersion":"jobsearcher.job.v1","id":"2586cdb2bb8f3613b9d38088","url":"https://jobsearcher.com/jobs/2586cdb2bb8f3613b9d38088","canonicalUrl":"https://jobsearcher.com/jobs/2586cdb2bb8f3613b9d38088","title":"Systems Software Engineer - ML Inference & GPU Clusters","description":"Raydar is seeking a Systems Software Engineer to work on low-level performance and infrastructure for a production ML serving platform in San Francisco, CA. You will tune software for speed, run large compute clusters, and interact with customers in a high-autonomy, high-ownership team.\r\nResponsibilities include delivering fast support for new models, improving the serving stack with batching and quantization, writing GPU kernels, and operating diverse compute clusters in a cost-efficient,#J-18808-Ljbffr","company":"JobLeads","rawCompany":"jobleadsus","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-12T01:11:52.233Z","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":"15-1211.00","title":"Computer Systems Analysts","slug":"computer-systems-analysts"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"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":"Systems Software Engineer - ML Inference & GPU Clusters","description":"Raydar is seeking a Systems Software Engineer to work on low-level performance and infrastructure for a production ML serving platform in San Francisco, CA. You will tune software for speed, run large compute clusters, and interact with customers in a high-autonomy, high-ownership team.\r\nResponsibilities include delivering fast support for new models, improving the serving stack with batching and quantization, writing GPU kernels, and operating diverse compute clusters in a cost-efficient,#J-18808-Ljbffr","datePosted":"2026-10-12T01:11:52.233Z","dateModified":"2026-10-12T01:11:52.233Z","hiringOrganization":{"@type":"Organization","name":"JobLeads","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"2586cdb2bb8f3613b9d38088"},"url":"https://jobsearcher.com/jobs/2586cdb2bb8f3613b9d38088"}}