{"schemaVersion":"jobsearcher.job.v1","id":"eeb4c835f073a3f4caa3e42b","url":"https://jobsearcher.com/jobs/eeb4c835f073a3f4caa3e42b","canonicalUrl":"https://jobsearcher.com/jobs/eeb4c835f073a3f4caa3e42b","title":"Inference Systems Engineer: Optimize AI Serving & Latency","description":"adaption is seeking an experienced engineer to own the cost and performance of our inference stack in the San Francisco Bay Area. You will influence throughput, latency, and reliability as workloads and hardware evolve.\nYou'll collaborate with the serving fleet engineers and own core levers like caching, batching, quantization, and decoding, ensuring efficient model serving without sacrificing quality.\n\n#J-18808-Ljbffr","company":"Adaption","rawCompany":"adaption","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-10-12T03:37:03.751Z","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":"518210","title":"Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services","slug":"computing-infrastructure-providers-data-processing-web-hosting-and-related-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Inference Systems Engineer: Optimize AI Serving & Latency","description":"adaption is seeking an experienced engineer to own the cost and performance of our inference stack in the San Francisco Bay Area. You will influence throughput, latency, and reliability as workloads and hardware evolve.\nYou'll collaborate with the serving fleet engineers and own core levers like caching, batching, quantization, and decoding, ensuring efficient model serving without sacrificing quality.\n\n#J-18808-Ljbffr","datePosted":"2026-10-12T03:37:03.751Z","dateModified":"2026-10-12T03:37:03.751Z","hiringOrganization":{"@type":"Organization","name":"Adaption","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"eeb4c835f073a3f4caa3e42b"},"url":"https://jobsearcher.com/jobs/eeb4c835f073a3f4caa3e42b"}}