{"schemaVersion":"jobsearcher.job.v1","id":"a2ad8bd3a51cb822d6d6679a","url":"https://jobsearcher.com/jobs/a2ad8bd3a51cb822d6d6679a","canonicalUrl":"https://jobsearcher.com/jobs/a2ad8bd3a51cb822d6d6679a","title":"Staff Engineer, Distributed GPU Clusters & Infra","description":"Causal Labs is building a Large Physics foundation Model and GPU-driven compute environment to enable rapid research iteration at scale. You will design, deploy, and operate massive GPU clusters, extending Kubernetes and Slurm for efficient, multi-tenant workloads.\nYou will own end-to-end stack from provisioning to observability, collaborating with researchers to optimize performance and placement. A strong systems background and experience with CUDA/NCCL are essential.\n\n#J-18808-Ljbffr","company":"Causal Labs","rawCompany":"causal labs","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-08-01T03:14:12.011Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"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":"541715","title":"Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)","slug":"research-and-development-in-the-physical-engineering-and-life-sciences-except-nanotechnology-and-biotechnology"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Staff Engineer, Distributed GPU Clusters & Infra","description":"Causal Labs is building a Large Physics foundation Model and GPU-driven compute environment to enable rapid research iteration at scale. You will design, deploy, and operate massive GPU clusters, extending Kubernetes and Slurm for efficient, multi-tenant workloads.\nYou will own end-to-end stack from provisioning to observability, collaborating with researchers to optimize performance and placement. A strong systems background and experience with CUDA/NCCL are essential.\n\n#J-18808-Ljbffr","datePosted":"2026-08-01T03:14:12.011Z","dateModified":"2026-08-01T03:14:12.011Z","hiringOrganization":{"@type":"Organization","name":"Causal Labs","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"a2ad8bd3a51cb822d6d6679a"},"url":"https://jobsearcher.com/jobs/a2ad8bd3a51cb822d6d6679a"}}