{"schemaVersion":"jobsearcher.job.v1","id":"be55ed9901e0d835d3ae8de5","url":"https://jobsearcher.com/jobs/be55ed9901e0d835d3ae8de5","canonicalUrl":"https://jobsearcher.com/jobs/be55ed9901e0d835d3ae8de5","title":"Inference Performance Engineer: Latency & Cost Optimization","description":"OpenAI is looking for a performance modeler in San Francisco who will analyze inference stack performance and build cost-to-serve estimates. In this role, candidates should have expertise in performance profiling and enjoy reasoning about distributed systems.\nThe position offers a compensation range of $295K to $555K and requires collaboration with engineering and research teams to enhance performance and address system bottlenecks.\n\n#J-18808-Ljbffr","company":"OpenAI","rawCompany":"openai","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-07-16T03:22:13.088Z","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":"15-2051.00","title":"Data Scientists","slug":"data-scientists"}],"industries":[{"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"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Inference Performance Engineer: Latency & Cost Optimization","description":"OpenAI is looking for a performance modeler in San Francisco who will analyze inference stack performance and build cost-to-serve estimates. In this role, candidates should have expertise in performance profiling and enjoy reasoning about distributed systems.\nThe position offers a compensation range of $295K to $555K and requires collaboration with engineering and research teams to enhance performance and address system bottlenecks.\n\n#J-18808-Ljbffr","datePosted":"2026-07-16T03:22:13.088Z","dateModified":"2026-07-16T03:22:13.088Z","hiringOrganization":{"@type":"Organization","name":"OpenAI","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"be55ed9901e0d835d3ae8de5"},"url":"https://jobsearcher.com/jobs/be55ed9901e0d835d3ae8de5"}}