{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/rlhf-pipelines"},"x-facet":{"type":"skill","slug":"rlhf-pipelines","display":"Rlhf Pipelines","count":1},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_854e95b5-76b"},"title":"Sr. Director of Product, Research and Training Infrastructure","description":"<p>CoreWeave is seeking a visionary Sr. Director of Product, Research Training Infrastructure to lead the product strategy and engineering execution for the services that power the most ambitious AI research labs in the world.</p>\n<p>This executive leader will own the product strategy and engineering execution for the Research Training Stack, focusing on the specialized orchestration, evaluation, and iteration tools required for massive-scale pre-training and post-training.</p>\n<p>Key responsibilities include:</p>\n<ul>\n<li>Frontier Orchestration: Oversee the evolution of SUNK (Slurm on Kubernetes) to provide researchers with deterministic, bare-metal performance through a cloud-native interface.</li>\n</ul>\n<ul>\n<li>Holistic Training Services: Drive the development of next-generation orchestrators and automated training-based evaluation frameworks that ensure model quality throughout the lifecycle.</li>\n</ul>\n<ul>\n<li>Post-Training Excellence: Build the infrastructure required for sophisticated Reinforcement Learning (RL) and RLHF pipelines, enabling labs to refine foundation models with maximum efficiency.</li>\n</ul>\n<ul>\n<li>Customer Advocacy: Act as the primary technical partner for lead researchers at global AI labs, translating their &#39;future-state&#39; requirements into actionable product roadmaps.</li>\n</ul>\n<p>Requirements include:</p>\n<ul>\n<li>Proven leadership experience in engineering leadership, with at least 5+ years managing large-scale infrastructure at a top-tier research lab or an AI-native cloud provider.</li>\n</ul>\n<ul>\n<li>Deep, hands-on knowledge of Slurm, Kubernetes, and the specific networking requirements (InfiniBand/RDMA) for distributed training clusters.</li>\n</ul>\n<ul>\n<li>Research mindset and understanding of the &#39;pain points&#39; of a research scientist.</li>\n</ul>\n<ul>\n<li>Scaling experience delivering mission-critical services on multi-thousand GPU clusters (H100/Blackwell/Rubin architectures).</li>\n</ul>\n<ul>\n<li>Strategic vision to define &#39;what&#39;s next&#39; in the AI stack, from automated RL loops to specialized sandbox environments.</li>\n</ul>\n<p>Why CoreWeave?</p>\n<p>In 2026, CoreWeave is the foundation of the largest infrastructure buildout in human history. We are building AI Factories, not just data centers.</p>\n<ul>\n<li>Silicon-Up Innovation: Work directly with the latest NVIDIA architectures.</li>\n</ul>\n<ul>\n<li>Impact: You will be the architect of the environment that enables the next new discovery.</li>\n</ul>\n<p>Velocity: We move at the speed of the researchers we support, bypassing legacy cloud bottlenecks to deliver raw power.</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_854e95b5-76b","directApply":true,"hiringOrganization":{"@type":"Organization","name":"CoreWeave","sameAs":"https://www.coreweave.com","logo":"https://logos.yubhub.co/coreweave.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/coreweave/jobs/4665964006","x-work-arrangement":"hybrid","x-experience-level":"executive","x-job-type":"full-time","x-salary-range":"$233,000 to $341,000","x-skills-required":["Slurm","Kubernetes","InfiniBand/RDMA","Distributed training clusters","GPU clusters","H100/Blackwell/Rubin architectures","Reinforcement Learning (RL)","RLHF pipelines"],"x-skills-preferred":[],"datePosted":"2026-04-18T15:50:11.130Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Livingston, NJ / New York, NY / Sunnyvale, CA / Bellevue, WA"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Slurm, Kubernetes, InfiniBand/RDMA, Distributed training clusters, GPU clusters, H100/Blackwell/Rubin architectures, Reinforcement Learning (RL), RLHF pipelines","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":233000,"maxValue":341000,"unitText":"YEAR"}}}]}