{"schemaVersion":"jobsearcher.job.v1","id":"86bb74ea87d960df7cdea3a0","url":"https://jobsearcher.com/jobs/86bb74ea87d960df7cdea3a0","canonicalUrl":"https://jobsearcher.com/jobs/86bb74ea87d960df7cdea3a0","title":"Data Ingestion Engineer for Large-Scale AI Training","description":"Reflection is a research lab focused on making intelligence open and accessible. We seek an engineer to build and operate large-scale data ingestion systems for pre-training, turning open web data into reliable corpora for frontier models.\r\nYou will own ingestion pipelines, run experiments, and collaborate with researchers to optimize data collection and model performance. This hybrid role suits those who love robust distributed systems and data-driven iteration.\r\nJ-18808-Ljbffr","company":"Socket","rawCompany":"socket","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-08-08T01:49:49.339Z","occupations":[{"code":"15-1243.01","title":"Data Warehousing Specialists","slug":"data-warehousing-specialists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"}],"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":"Data Ingestion Engineer for Large-Scale AI Training","description":"Reflection is a research lab focused on making intelligence open and accessible. We seek an engineer to build and operate large-scale data ingestion systems for pre-training, turning open web data into reliable corpora for frontier models.\r\nYou will own ingestion pipelines, run experiments, and collaborate with researchers to optimize data collection and model performance. This hybrid role suits those who love robust distributed systems and data-driven iteration.\r\nJ-18808-Ljbffr","datePosted":"2026-08-08T01:49:49.339Z","dateModified":"2026-08-08T01:49:49.339Z","hiringOrganization":{"@type":"Organization","name":"Socket","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"86bb74ea87d960df7cdea3a0"},"url":"https://jobsearcher.com/jobs/86bb74ea87d960df7cdea3a0"}}