{"schemaVersion":"jobsearcher.job.v1","id":"b03ebba8ebf5b275c054e524","url":"https://jobsearcher.com/jobs/b03ebba8ebf5b275c054e524","canonicalUrl":"https://jobsearcher.com/jobs/b03ebba8ebf5b275c054e524","title":"Senior Python Engineer: AI Evaluation Architect (Remote)","description":"Mindrift is seeking Experienced software developers for a project-based role to build a dataset evaluating AI coding agents. You will craft realistic developer environments, define tasks, and write tests that accommodate multiple correct solutions while ensuring robustness.\r\nResponsibilities include designing evaluation criteria, iterating with QA feedback, and collaborating with a team to deliver fair assessments. Strong Python, React, Docker, and data-workflow experience is valuable.\r\nJ-18808-Ljbffr","company":"Mind Rift","rawCompany":"mind rift","city":"San Antonio","state":"TX","isRemote":true,"isActive":false,"createdAt":"2026-08-08T01:55:57.079Z","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 Python Engineer: AI Evaluation Architect (Remote)","description":"Mindrift is seeking Experienced software developers for a project-based role to build a dataset evaluating AI coding agents. You will craft realistic developer environments, define tasks, and write tests that accommodate multiple correct solutions while ensuring robustness.\r\nResponsibilities include designing evaluation criteria, iterating with QA feedback, and collaborating with a team to deliver fair assessments. Strong Python, React, Docker, and data-workflow experience is valuable.\r\nJ-18808-Ljbffr","datePosted":"2026-08-08T01:55:57.079Z","dateModified":"2026-08-08T01:55:57.079Z","hiringOrganization":{"@type":"Organization","name":"Mind Rift","sameAs":"https://jobsearcher.com"},"jobLocationType":"TELECOMMUTE","applicantLocationRequirements":{"@type":"Country","name":"US"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Antonio","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"b03ebba8ebf5b275c054e524"},"url":"https://jobsearcher.com/jobs/b03ebba8ebf5b275c054e524"}}