{"schemaVersion":"jobsearcher.job.v1","id":"2f80fcd18f01fe190fde171f","url":"https://jobsearcher.com/jobs/2f80fcd18f01fe190fde171f","canonicalUrl":"https://jobsearcher.com/jobs/2f80fcd18f01fe190fde171f","title":"Senior Software Engineer, Distributed Systems Engineer - DGX Cloud","description":"OverviewIn this role you will help scale production AI GPU clusters by developing Kubernetes-based scheduling and resource-management software. You will work on DGX Cloud production systems, ensuring reliability and performance across multi-team initiatives. You will analyze failures through incident management and leverage telemetry from GPUs, clusters, and networks. This is a hands-on position that values creativity and execution, offering impact on cutting-edge AI infrastructure. You will collaborate with cross-functional teams to advance NVIDIA's AI deployment capabilities.Compensation / Benefitsequitybenefitsbase salary with levels 3 and 4remote work optionslocation: Santa Clara or US Remotecareer growth opportunitiesResponsibilitiesDevelop and extend Kubernetes-based scheduling for GPU resourcesBuild and improve cluster health monitoring and incident response processesWork on production systems for large scalable GPU clustersIntegrate hardware diagnostics and telemetry into reliability toolingCollaborate with cross-functional teams to maintain high performance and reliabilityEvaluate failures and implement improvements via a defined incident management approachKey requirements5+ years in a software engineering role on large-scale production systemsSoftware development with Kubernetes APIs and frameworks (not only operations)BS in Computer Science, Engineering, Physics, Mathematics or equivalentProficiency in Go or Python and strong data structures/algorithmsStrong communication and cross-functional collaboration skillsstrong communicationcross-functional collaborationexecution biasKubernetes APIs and cluster managementGo or Python programmingGPU resource scheduling","company":"NVIDIA","rawCompany":"nvidia","city":"Plano","state":"TX","isRemote":false,"isActive":false,"createdAt":"2026-10-26T13:22:27.089Z","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":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Senior Software Engineer, Distributed Systems Engineer - DGX Cloud","description":"OverviewIn this role you will help scale production AI GPU clusters by developing Kubernetes-based scheduling and resource-management software. You will work on DGX Cloud production systems, ensuring reliability and performance across multi-team initiatives. You will analyze failures through incident management and leverage telemetry from GPUs, clusters, and networks. This is a hands-on position that values creativity and execution, offering impact on cutting-edge AI infrastructure. You will collaborate with cross-functional teams to advance NVIDIA's AI deployment capabilities.Compensation / Benefitsequitybenefitsbase salary with levels 3 and 4remote work optionslocation: Santa Clara or US Remotecareer growth opportunitiesResponsibilitiesDevelop and extend Kubernetes-based scheduling for GPU resourcesBuild and improve cluster health monitoring and incident response processesWork on production systems for large scalable GPU clustersIntegrate hardware diagnostics and telemetry into reliability toolingCollaborate with cross-functional teams to maintain high performance and reliabilityEvaluate failures and implement improvements via a defined incident management approachKey requirements5+ years in a software engineering role on large-scale production systemsSoftware development with Kubernetes APIs and frameworks (not only operations)BS in Computer Science, Engineering, Physics, Mathematics or equivalentProficiency in Go or Python and strong data structures/algorithmsStrong communication and cross-functional collaboration skillsstrong communicationcross-functional collaborationexecution biasKubernetes APIs and cluster managementGo or Python programmingGPU resource scheduling","datePosted":"2026-10-26T13:22:27.089Z","dateModified":"2026-10-26T13:22:27.089Z","hiringOrganization":{"@type":"Organization","name":"NVIDIA","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Plano","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"2f80fcd18f01fe190fde171f"},"url":"https://jobsearcher.com/jobs/2f80fcd18f01fe190fde171f"}}