{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/autonomous-workflows"},"x-facet":{"type":"skill","slug":"autonomous-workflows","display":"Autonomous Workflows","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_f5253558-a19"},"title":"IC Agentic Engineering Manager - Stargate","description":"<p>We are seeking an IC Agentic Engineering Manager to lead the development and application of agent-based systems for infrastructure delivery and operations within Stargate.</p>\n<p>This is a player-coach role: you will contribute directly to system design and implementation while leading a small team. You will focus on applying agentic systems to infrastructure workflows such as deployment orchestration, system bring-up, issue triage, debugging, and capacity management.</p>\n<p>This role is not focused on building general-purpose agent platforms. Instead, it is centered on applying agentic systems to solve concrete infrastructure problems, working closely with hardware, networking, and cluster teams.</p>\n<p><strong>Key Responsibilities</strong></p>\n<ul>\n<li>Design and build agent-based systems to support infrastructure deployment and operations</li>\n</ul>\n<ul>\n<li>Identify high-impact opportunities to apply agents across workflows such as:</li>\n</ul>\n<ul>\n<li>cluster bring-up and deployment readiness</li>\n</ul>\n<ul>\n<li>incident triage and root cause analysis</li>\n</ul>\n<ul>\n<li>system validation and health monitoring</li>\n</ul>\n<ul>\n<li>capacity management and operational decision-making</li>\n</ul>\n<ul>\n<li>Lead a small team while contributing directly as an IC across system design, development, and integration</li>\n</ul>\n<ul>\n<li>Partner with infrastructure, hardware, and networking teams to integrate agentic systems into production workflows</li>\n</ul>\n<ul>\n<li>Develop systems that leverage telemetry, logs, and system signals to enable closed-loop automation</li>\n</ul>\n<ul>\n<li>Define evaluation frameworks to measure system effectiveness, reliability, and operational impact</li>\n</ul>\n<ul>\n<li>Drive iteration from prototype to production, ensuring robustness and scalability</li>\n</ul>\n<p><strong>Qualifications</strong></p>\n<ul>\n<li>Strong software engineering background in distributed systems, infrastructure, or platform engineering</li>\n</ul>\n<ul>\n<li>Experience building production automation systems or data-driven operational tooling</li>\n</ul>\n<ul>\n<li>Experience applying AI, ML, or agent-based approaches to real-world systems or workflows</li>\n</ul>\n<ul>\n<li>Ability to operate as a hands-on IC while leading a small team</li>\n</ul>\n<ul>\n<li>Experience working cross-functionally with infrastructure, hardware, or systems teams</li>\n</ul>\n<ul>\n<li>Strong problem-solving skills in complex, ambiguous environments</li>\n</ul>\n<p><strong>Preferred Skills</strong></p>\n<ul>\n<li>Experience with LLM-based systems, agents, or autonomous workflows</li>\n</ul>\n<ul>\n<li>Background in infrastructure operations, SRE, or large-scale system deployment</li>\n</ul>\n<ul>\n<li>Experience working on cluster bring-up, debugging, or data center infrastructure systems</li>\n</ul>\n<ul>\n<li>Familiarity with telemetry, monitoring systems, and observability pipelines</li>\n</ul>\n<ul>\n<li>Experience building internal tools or platforms for engineering productivity and operations</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_f5253558-a19","directApply":true,"hiringOrganization":{"@type":"Organization","name":"OpenAI","sameAs":"https://openai.com/","logo":"https://logos.yubhub.co/openai.com.png"},"x-apply-url":"https://jobs.ashbyhq.com/openai/4509797c-7e8b-4bfd-a68e-fb3fd90d2433","x-work-arrangement":"onsite","x-experience-level":"mid","x-job-type":"Full time","x-salary-range":"$293K – $490K","x-skills-required":["software engineering","distributed systems","infrastructure","platform engineering","production automation","data-driven operational tooling","AI","ML","agent-based approaches"],"x-skills-preferred":["LLM-based systems","agents","autonomous workflows","infrastructure operations","SRE","large-scale system deployment","cluster bring-up","debugging","data center infrastructure systems","telemetry","monitoring systems","observability pipelines","internal tools","platforms","engineering productivity"],"datePosted":"2026-04-24T12:21:41.255Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"software engineering, distributed systems, infrastructure, platform engineering, production automation, data-driven operational tooling, AI, ML, agent-based approaches, LLM-based systems, agents, autonomous workflows, infrastructure operations, SRE, large-scale system deployment, cluster bring-up, debugging, data center infrastructure systems, telemetry, monitoring systems, observability pipelines, internal tools, platforms, engineering productivity","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":293000,"maxValue":490000,"unitText":"YEAR"}}}]}