{"schemaVersion":"jobsearcher.job.v1","id":"8a1651efba683667f2ee4898","url":"https://jobsearcher.com/jobs/8a1651efba683667f2ee4898","canonicalUrl":"https://jobsearcher.com/jobs/8a1651efba683667f2ee4898","title":"Principal GPU Inference Reliability Engineer","description":"Together Computer Inc. is seeking a reliability-minded software engineer to own the production lifecycle of the GPU inference fleet and the Kubernetes‑native control plane that provisions clusters, models, and capacity.\r\nYou will triage InfiniBand/RDMA issues and extend automated self‑healing to reduce outages across fleet scale. You’ll own SLOs and error budgets for inference serving, drive incident response, and translate postmortems into durable improvements in controllers, automation, and#J-18808-Ljbffr","company":"Together Computer","rawCompany":"together computer","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-11-04T02:17:02.618Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"11-3021.00","title":"Computer and Information Systems Managers","slug":"computer-and-information-systems-managers"},{"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":"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":"Principal GPU Inference Reliability Engineer","description":"Together Computer Inc. is seeking a reliability-minded software engineer to own the production lifecycle of the GPU inference fleet and the Kubernetes‑native control plane that provisions clusters, models, and capacity.\r\nYou will triage InfiniBand/RDMA issues and extend automated self‑healing to reduce outages across fleet scale. You’ll own SLOs and error budgets for inference serving, drive incident response, and translate postmortems into durable improvements in controllers, automation, and#J-18808-Ljbffr","datePosted":"2026-11-04T02:17:02.618Z","dateModified":"2026-11-04T02:17:02.618Z","hiringOrganization":{"@type":"Organization","name":"Together Computer","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"8a1651efba683667f2ee4898"},"url":"https://jobsearcher.com/jobs/8a1651efba683667f2ee4898"}}