{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/ml-stacks"},"x-facet":{"type":"skill","slug":"ml-stacks","display":"Ml Stacks","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_26b9d76f-c85"},"title":"Research Engineer, Universes","description":"<p>We&#39;re looking for Research Engineers to help us build the next generation of training environments for capable and safe agentic AI.</p>\n<p>This role blends research and engineering responsibilities, requiring you to both implement novel approaches and contribute to research direction. You&#39;ll work on fundamental research in reinforcement learning, designing training environments and methodologies that push the state of the art, and building evaluations that measure genuine capability.</p>\n<p>Responsibilities:</p>\n<ul>\n<li>Build the next generation of agentic environments</li>\n<li>Build rigorous evaluations that measure real capability</li>\n<li>Collaborate across research and infrastructure teams to ship environments into production training</li>\n<li>Debug and iterate rapidly across research and production ML stacks</li>\n<li>Contribute to research culture through technical discussions and collaborative problem-solving</li>\n</ul>\n<p>You may be a good fit if you:</p>\n<ul>\n<li>Are highly impact-driven , you care about outcomes, not activity</li>\n<li>Operate with high agency</li>\n<li>Have good research taste or senior technical experience, demonstrating good judgment in identifying what actually matters in complex problem spaces</li>\n<li>Can balance research exploration with engineering implementation</li>\n<li>Are passionate about the potential impact of AI and are committed to developing safe and beneficial systems</li>\n<li>Are comfortable with uncertainty and adapt quickly as the landscape shifts</li>\n<li>Have strong software engineering skills and can build robust infrastructure</li>\n<li>Enjoy pair programming (we love to pair!)</li>\n</ul>\n<p>Strong candidates may also have one or more of the following:</p>\n<ul>\n<li>Have industry experience with large language model training, fine-tuning or evaluation</li>\n<li>Have industry experience building RL environments, simulation systems, or large-scale ML infrastructure</li>\n<li>Senior experience in a relevant technical field even if transitioning domains</li>\n<li>Deep expertise in sandboxing, containerization, VM infrastructure, or distributed systems</li>\n<li>Published influential work in relevant ML areas</li>\n</ul>\n<p>The annual compensation range for this role is $500,000-$850,000 USD.</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_26b9d76f-c85","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://www.anthropic.com/","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/5061517008","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$500,000-$850,000 USD","x-skills-required":["Reinforcement learning","Training environments","ML stacks","Software engineering","Pair programming"],"x-skills-preferred":["Large language model training","RL environments","Simulation systems","Distributed systems"],"datePosted":"2026-04-18T15:46:02.776Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Remote-Friendly (Travel-Required) | San Francisco, CA | Seattle, WA | New York City, NY"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Reinforcement learning, Training environments, ML stacks, Software engineering, Pair programming, Large language model training, RL environments, Simulation systems, Distributed systems","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":500000,"maxValue":850000,"unitText":"YEAR"}}}]}