{"schemaVersion":"jobsearcher.job.v1","id":"a6df37edd8997845a170d36a","url":"https://jobsearcher.com/jobs/a6df37edd8997845a170d36a","canonicalUrl":"https://jobsearcher.com/jobs/a6df37edd8997845a170d36a","title":"Senior Software Engineer, Agentic Coding RL Environments - AI Trainer","description":"About the job About Surge AI\n\nSurge AI partners with the world's leading AI labs to build the benchmarks and RL environments that train and evaluate frontier models. Most benchmarks cut corners because expert humans are expensive. Our model is the opposite: we pay experts enough that we don't have to.\n\nPosition: Senior Software Engineer (Agentic Coding RL Environments)\n\nType: Contract\n\nCompensation: $100–150+/hour ($200–300k+/year). Rates scale with your experience, and many go past the top of that range.\n\nLocation: Fully remote, any time zone\n\nRole Responsibilities\nBuild coding RL environments and benchmarks that test how agents perform on realistic software engineering tasks\nDesign tasks based on real engineering work\nReview and red-team model output to surface meaningful failures\nWrite the tests, rubrics, and success criteria that separate good work from slop\nGive structured feedback that improves future models\nQualifications Must-Have\nProfessional software engineering experience shipping real, scaled production systems\nExpertise in at least one common tech stack (TypeScript, Python, Ruby, PHP, Java, Rust, Go, or C++)\nStrong judgment about what \"good code\" and a \"meaningful model failure\" look like\nComfort working independently, and giving direct, code-review-style feedback\nAvailability for a meaningful commitment (most contributors work 20 to 40+ hours per week)\n\nNote: You do not need prior AI or ML experience. Strong engineering judgment and attention to detail matter most.\n\nWhat makes this different\nNo managers, 1:1s, OKR ceremonies, or Jira backlog grooming\nYou choose when and where you work\nYou are judged on the quality of what you produce, not speed\nApplication Process\nCoding capability screen (replaces a multi-round interview loop)\nID verification\nBackground check\nPaid first real task. Do well, and you're on the team.\n\nQuestions? swe@surgehq.ai","company":"Surge Ai","rawCompany":"surge ai","city":"Bothell","state":"WA","isRemote":false,"isActive":false,"createdAt":"2026-08-24T09:07:21.986Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1251.00","title":"Computer Programmers","slug":"computer-programmers"},{"code":"15-1254.00","title":"Web Developers","slug":"web-developers"}],"industries":[{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Senior Software Engineer, Agentic Coding RL Environments - AI Trainer","description":"About the job About Surge AI\n\nSurge AI partners with the world's leading AI labs to build the benchmarks and RL environments that train and evaluate frontier models. Most benchmarks cut corners because expert humans are expensive. Our model is the opposite: we pay experts enough that we don't have to.\n\nPosition: Senior Software Engineer (Agentic Coding RL Environments)\n\nType: Contract\n\nCompensation: $100–150+/hour ($200–300k+/year). Rates scale with your experience, and many go past the top of that range.\n\nLocation: Fully remote, any time zone\n\nRole Responsibilities\nBuild coding RL environments and benchmarks that test how agents perform on realistic software engineering tasks\nDesign tasks based on real engineering work\nReview and red-team model output to surface meaningful failures\nWrite the tests, rubrics, and success criteria that separate good work from slop\nGive structured feedback that improves future models\nQualifications Must-Have\nProfessional software engineering experience shipping real, scaled production systems\nExpertise in at least one common tech stack (TypeScript, Python, Ruby, PHP, Java, Rust, Go, or C++)\nStrong judgment about what \"good code\" and a \"meaningful model failure\" look like\nComfort working independently, and giving direct, code-review-style feedback\nAvailability for a meaningful commitment (most contributors work 20 to 40+ hours per week)\n\nNote: You do not need prior AI or ML experience. Strong engineering judgment and attention to detail matter most.\n\nWhat makes this different\nNo managers, 1:1s, OKR ceremonies, or Jira backlog grooming\nYou choose when and where you work\nYou are judged on the quality of what you produce, not speed\nApplication Process\nCoding capability screen (replaces a multi-round interview loop)\nID verification\nBackground check\nPaid first real task. Do well, and you're on the team.\n\nQuestions? swe@surgehq.ai","datePosted":"2026-08-24T09:07:21.986Z","dateModified":"2026-08-24T09:07:21.986Z","hiringOrganization":{"@type":"Organization","name":"Surge Ai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Bothell","addressRegion":"WA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"a6df37edd8997845a170d36a"},"url":"https://jobsearcher.com/jobs/a6df37edd8997845a170d36a"}}