{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/scalability-concepts"},"x-facet":{"type":"skill","slug":"scalability-concepts","display":"Scalability Concepts","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_04ee7215-acf"},"title":"Sr. Manager, Engineering - Model Serving","description":"<p>At Databricks, we enable data teams to solve the world&#39;s toughest problems by building and running the world&#39;s best data and AI infrastructure platform. Our Model Serving product provides enterprises with a unified, scalable, and governed platform to deploy and manage AI/ML models. As a Senior Engineering Manager, you will lead the team owning both the product experience and the foundational infrastructure of Model Serving, shaping customer-facing capabilities while designing for scalability, extensibility, and performance across both CPU and GPU inference. The impact you will have includes leading, mentoring, and growing a high-performing engineering team, defining and owning the product and technical roadmap for Model Serving, collaborating closely with product, research, platform, and infrastructure teams, and ensuring Model Serving meets stringent SLAs, SLOs, and performance and reliability goals.</p>\n<p>Key responsibilities include:</p>\n<ul>\n<li>Leading, mentoring, and growing a high-performing engineering team responsible for both the customer-facing Model Serving product and its foundational infrastructure.</li>\n<li>Defining and owning the product and technical roadmap for Model Serving, balancing customer experience, functionality, and foundational investments across deployment, inference, monitoring, and scaling.</li>\n<li>Collaborating closely with product, research, platform, and infrastructure teams to drive end-to-end delivery from ideation and prioritization to launch and operation.</li>\n<li>Ensuring Model Serving meets stringent SLAs, SLOs, and performance and reliability goals, continuously improving operational efficiency and customer experience.</li>\n<li>Driving architectural decisions and product design around latency, throughput, autoscaling, GPU/CPU placement, and cost optimization.</li>\n<li>Advocating for customer needs through direct engagement, ensuring engineering decisions translate to clear product impact.</li>\n<li>Promoting best practices in code quality, testing, observability, and operational readiness.</li>\n<li>Fostering a culture of excellence, inclusion, and continuous improvement across the team.</li>\n<li>Partnering with recruiting to attract, hire, and develop top-tier engineering talent.</li>\n</ul>\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_04ee7215-acf","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Databricks","sameAs":"https://databricks.com","logo":"https://logos.yubhub.co/databricks.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/databricks/jobs/8211957002","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$217,000-$312,200 USD","x-skills-required":["technical leadership","large-scale distributed systems","real-time serving systems","architectural design","operational excellence","production systems","SLAs","SLOs","GPU performance optimization","concurrency","caching","scalability concepts"],"x-skills-preferred":[],"datePosted":"2026-04-18T15:58:02.797Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, California"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"technical leadership, large-scale distributed systems, real-time serving systems, architectural design, operational excellence, production systems, SLAs, SLOs, GPU performance optimization, concurrency, caching, scalability concepts","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":217000,"maxValue":312200,"unitText":"YEAR"}}}]}