{"schemaVersion":"jobsearcher.job.v1","id":"bb48b8e9682f31989203042f","url":"https://jobsearcher.com/jobs/bb48b8e9682f31989203042f","canonicalUrl":"https://jobsearcher.com/jobs/bb48b8e9682f31989203042f","title":"Inference Engineer: High-Throughput ML Serving","description":"Adaption Labs, Inc. is seeking an ML systems engineer to own the cost and performance of the inference stack. You will optimize caching, batching, quantization, decoding, and kernel-level tuning to improve throughput and latency while preserving model quality.\r\nYou will collaborate with the serving fleet engineers and tackle real production workloads, focusing on cost-efficiency, tail latency, and reliable delivery across changing workloads and hardware. Bay Area presence required.#J-18808-Ljbffr","company":"Adaption Labs","rawCompany":"adaption labs","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-10T01:22:50.439Z","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":"15-1244.00","title":"Network and Computer Systems Administrators","slug":"network-and-computer-systems-administrators"}],"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":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Inference Engineer: High-Throughput ML Serving","description":"Adaption Labs, Inc. is seeking an ML systems engineer to own the cost and performance of the inference stack. You will optimize caching, batching, quantization, decoding, and kernel-level tuning to improve throughput and latency while preserving model quality.\r\nYou will collaborate with the serving fleet engineers and tackle real production workloads, focusing on cost-efficiency, tail latency, and reliable delivery across changing workloads and hardware. Bay Area presence required.#J-18808-Ljbffr","datePosted":"2026-10-10T01:22:50.439Z","dateModified":"2026-10-10T01:22:50.439Z","hiringOrganization":{"@type":"Organization","name":"Adaption Labs","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"bb48b8e9682f31989203042f"},"url":"https://jobsearcher.com/jobs/bb48b8e9682f31989203042f"}}