{"schemaVersion":"jobsearcher.job.v1","id":"5a054b16b7896794a3ecb992","url":"https://jobsearcher.com/jobs/5a054b16b7896794a3ecb992","canonicalUrl":"https://jobsearcher.com/jobs/5a054b16b7896794a3ecb992","title":"ML Inference Performance Engineer Optimize Cost & Latency","description":"Adaption Labs in San Francisco is looking for a senior ML systems engineer to own the cost and performance of the inference stack. You’ll optimize caching, batching, quantization, and kernel-level performance to improve throughput and reduce latency without sacrificing model quality.\r\nYou’ll collaborate with the serving fleet engineers and tune routing, profiling, and measurement systems across production workloads. A strong background in Python/C++/Rust and GPU optimization is required.#J-18808-Ljbffr","company":"Adaption Labs","rawCompany":"adaption labs","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-04T03:05:47.592Z","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":"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":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"ML Inference Performance Engineer Optimize Cost & Latency","description":"Adaption Labs in San Francisco is looking for a senior ML systems engineer to own the cost and performance of the inference stack. You’ll optimize caching, batching, quantization, and kernel-level performance to improve throughput and reduce latency without sacrificing model quality.\r\nYou’ll collaborate with the serving fleet engineers and tune routing, profiling, and measurement systems across production workloads. A strong background in Python/C++/Rust and GPU optimization is required.#J-18808-Ljbffr","datePosted":"2026-10-04T03:05:47.592Z","dateModified":"2026-10-04T03:05:47.592Z","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":"5a054b16b7896794a3ecb992"},"url":"https://jobsearcher.com/jobs/5a054b16b7896794a3ecb992"}}