{"schemaVersion":"jobsearcher.job.v1","id":"b658507e69cf8d2b6ad94e89","url":"https://jobsearcher.com/jobs/b658507e69cf8d2b6ad94e89","canonicalUrl":"https://jobsearcher.com/jobs/b658507e69cf8d2b6ad94e89","title":"SRE - Compute & Hyperscale GPU Fleet Reliability","description":"Fluidstack is seeking a Production Engineer to own compute fleet health end-to-end, build the observability and automation that scales GPU infrastructure, and drive reliability across Kubernetes-managed and bare-metal environments. You will define failure modes, implement triage automation, and own the GPU qualification and firmware tooling.\nThe role emphasizes end-to-end ownership, rapid incident response, and fluency with AI tooling and modern automation.\n\n#J-18808-Ljbffr","company":"FluidStack","rawCompany":"fluidstack","city":"New York","state":"NY","isRemote":false,"isActive":false,"createdAt":"2026-07-16T03:44:59.606Z","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":"15-1299.00","title":"Computer Occupations, All Other","slug":"computer-occupations-all-other"}],"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":"SRE - Compute & Hyperscale GPU Fleet Reliability","description":"Fluidstack is seeking a Production Engineer to own compute fleet health end-to-end, build the observability and automation that scales GPU infrastructure, and drive reliability across Kubernetes-managed and bare-metal environments. You will define failure modes, implement triage automation, and own the GPU qualification and firmware tooling.\nThe role emphasizes end-to-end ownership, rapid incident response, and fluency with AI tooling and modern automation.\n\n#J-18808-Ljbffr","datePosted":"2026-07-16T03:44:59.606Z","dateModified":"2026-07-16T03:44:59.606Z","hiringOrganization":{"@type":"Organization","name":"FluidStack","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"New York","addressRegion":"NY","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"b658507e69cf8d2b6ad94e89"},"url":"https://jobsearcher.com/jobs/b658507e69cf8d2b6ad94e89"}}