{"schemaVersion":"jobsearcher.job.v1","id":"3a3823bbc989a261dd16d7fa","url":"https://jobsearcher.com/jobs/3a3823bbc989a261dd16d7fa","canonicalUrl":"https://jobsearcher.com/jobs/3a3823bbc989a261dd16d7fa","title":"ML Infrastructure Engineer","description":"ML Infrastructure EngineerWe are looking for an ML Infrastructure Engineer with 3+ years of experience to own and scale the training and inference stack at a fast-growing AI document processing platform. You'll be a strong generalist who understands the mechanics of how ML models work – from serving and monitoring to building robust data pipelines – and can improve inference performance, reliability, and cost efficiency. This is a high-impact IC role where you'll work closely with ML researchers to ensure models are deployed quickly and reliably, and that infrastructure is never a bottleneck for the products being served. The ideal candidate is AI-native from the get-go, comfortable with 1-to-3 node training and single-to-double node serving, and thrives in a fast-paced startup environment.\r\nWhat you will be doing:\r\nBuilding and maintaining model serving infrastructure – improving inference speed, monitoring, and reliability to ensure it's never a bottleneck for customers\r\nSetting up and improving training infrastructure for models ranging from 300M to 30B parameters across 1-to-3 node environments\r\nDeveloping observability, logging, and monitoring systems across the ML stack\r\nBuilding internal data pipelines and tooling to help ML researchers move faster from experiment to production\r\nArchitecting infrastructure to arbitrate inference between multiple cloud providers while optimizing for accuracy, latency, and cost","company":"Hsf","rawCompany":"hsf","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-11-20T01:38:51.645Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1244.00","title":"Network and Computer Systems Administrators","slug":"network-and-computer-systems-administrators"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"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":"541519","title":"Other Computer Related Services","slug":"other-computer-related-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"ML Infrastructure Engineer","description":"ML Infrastructure EngineerWe are looking for an ML Infrastructure Engineer with 3+ years of experience to own and scale the training and inference stack at a fast-growing AI document processing platform. You'll be a strong generalist who understands the mechanics of how ML models work – from serving and monitoring to building robust data pipelines – and can improve inference performance, reliability, and cost efficiency. This is a high-impact IC role where you'll work closely with ML researchers to ensure models are deployed quickly and reliably, and that infrastructure is never a bottleneck for the products being served. The ideal candidate is AI-native from the get-go, comfortable with 1-to-3 node training and single-to-double node serving, and thrives in a fast-paced startup environment.\r\nWhat you will be doing:\r\nBuilding and maintaining model serving infrastructure – improving inference speed, monitoring, and reliability to ensure it's never a bottleneck for customers\r\nSetting up and improving training infrastructure for models ranging from 300M to 30B parameters across 1-to-3 node environments\r\nDeveloping observability, logging, and monitoring systems across the ML stack\r\nBuilding internal data pipelines and tooling to help ML researchers move faster from experiment to production\r\nArchitecting infrastructure to arbitrate inference between multiple cloud providers while optimizing for accuracy, latency, and cost","datePosted":"2026-11-20T01:38:51.645Z","dateModified":"2026-11-20T01:38:51.645Z","hiringOrganization":{"@type":"Organization","name":"Hsf","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"3a3823bbc989a261dd16d7fa"},"url":"https://jobsearcher.com/jobs/3a3823bbc989a261dd16d7fa"}}