{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/agent-behaviour"},"x-facet":{"type":"skill","slug":"agent-behaviour","display":"Agent Behaviour","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_ac106023-129"},"title":"Software Engineer","description":"<p><strong>About the Role</strong></p>\n<p>As a Software Engineer on the Agent Harness team at Cursor, you&#39;ll build the core agent behaviour and capabilities that power agent experiences across Cursor products. This spans agent orchestration, tools, guardrails, and model behaviour tuning,designed as a platform that Cursor engineers can extend and depend on.</p>\n<p>Your work will also define the default Cursor agent experience (\\&quot;Auto\\&quot;), where users trust us to make the right model choices under real-world constraints.</p>\n<p><strong>Responsibilities</strong></p>\n<ul>\n<li>Advance the agent harness (agent loop, tools, prompts, execution environment, capabilities) used across Cursor products. This would shape and empower experiences like multi-agent coordination.</li>\n</ul>\n<ul>\n<li>Improve the default Cursor agent experience (the \\&quot;Auto\\&quot; model setting): making smart model choices based on user needs, model capabilities, and cost appetite.</li>\n</ul>\n<ul>\n<li>Shape the default Cursor agent&#39;s personality.</li>\n</ul>\n<ul>\n<li>Launch new models on Cursor end-to-end , partnering with foundational model providers and our research team on integration, evaluation, and rollout.</li>\n</ul>\n<p><strong>Requirements</strong></p>\n<ul>\n<li>You have built complex agentic products or infrastructure.</li>\n</ul>\n<ul>\n<li>You have strong software engineering fundamentals and enjoy shipping production systems.</li>\n</ul>\n<ul>\n<li>You have taste and strong opinions on model and agent behaviours. You stay up-to-date and informed on emerging research and industry trends.</li>\n</ul>\n<ul>\n<li>You make good calls in the grey area: weighing data, user experience, and product taste when there isn&#39;t a single \\&quot;right\\&quot; answer.</li>\n</ul>\n<ul>\n<li>Experience building eval datasets or frameworks to understand and improve the performance of AI systems is a plus.</li>\n</ul>\n<ul>\n<li>Experience building products or tools used by other engineers is a plus.</li>\n</ul>\n<p><strong>Benefits</strong></p>\n<p>This role offers a competitive salary and opportunities for growth and development within the company.</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_ac106023-129","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Cursor","sameAs":"https://cursor.com","logo":"https://logos.yubhub.co/cursor.com.png"},"x-apply-url":"https://cursor.com/careers/software-engineer-agent-harness","x-work-arrangement":"remote","x-experience-level":"mid","x-job-type":"full-time","x-salary-range":"\",   \"salaryMin\": 95000,   \"salaryMax\": 110000,   \"salaryCurrency\": \"USD\",   \"salaryPeriod\": \"year","x-skills-required":["software engineering","agent behaviour","model behaviour","AI systems","multi-agent coordination"],"x-skills-preferred":["eval datasets","frameworks","product development","tool development"],"datePosted":"2026-04-24T14:08:41.480Z","jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"software engineering, agent behaviour, model behaviour, AI systems, multi-agent coordination, eval datasets, frameworks, product development, tool development","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":95000,"maxValue":110000,"unitText":"YEAR"}}}]}