{"schemaVersion":"jobsearcher.job.v1","id":"2005dd8cc030930fd12b5b69","url":"https://jobsearcher.com/jobs/2005dd8cc030930fd12b5b69","canonicalUrl":"https://jobsearcher.com/jobs/2005dd8cc030930fd12b5b69","title":"MCP & Tools Python Developer - Agent Evaluation Infrastructure","description":"This opportunity is only for candidates currently residing in the specified country. Your location may affect eligibility and rates. Please submit your resume in English and indicate your level of English proficiency.\r\nAt Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of AI.\r\nWhat We Do\r\nThe Mindrift platform, launched and powered by Toloka, connects domain experts with cutting-edge AI projects from innovative tech clients. Our mission is to unlock the potential of GenAI by tapping into real-world expertise from across the globe.\r\nWho We're Looking For\r\nCalling all security researchers, engineers, and penetration testers with a strong foundation in problem-solving, offensive security, and AI-related risk assessment. If you thrive on digging into complex systems, uncovering hidden vulnerabilities, and thinking creatively under constraints, join us! We're looking for someone who can bring a hands-on approach to technical challenges, whether breaking into systems to expose weaknesses or building secure tools and processes. We value contributors with a passion for continuous learning, experimentation, and adaptability.\r\nAbout the Project\r\nWe're on the hunt for hands-on Python engineers for a new project focused on developing Model Context Protocol (MCP) servers and internal tools for running and evaluating agent behavior. You'll implement base methods for agent action verification, integrate with internal and client infrastructures, and help fill tooling gaps across the team.\r\nWhat You'll Be Doing\r\nDeveloping and maintaining MCP-compatible evaluation servers\r\nImplementing logic to check agent actions against scenario definitions\r\nCreating or extending tools that writers and QAs use to test agents\r\nWorking closely with infrastructure engineers to ensure compatibility\r\nOccasionally helping with test writing or debug sessions when needed\r\nAlthough we're only looking for experts for this current project, contributors with consistent high-quality submissions may receive an invitation for ongoing collaboration across future projects.\r\nHow to Get Started\r\nApply to this post, qualify, and get the chance to contribute to a project aligned with your skills, on your own schedule. Shape the future of AI while building tools that benefit everyone.\r\nRequirements\r\nThe ideal contributor will have\r\n4+ years of Python development experience, ideally in backend or tools\r\nSolid experience building APIs, testing frameworks, or protocol-based interfaces\r\nUnderstanding of Docker, Linux CLI, and HTTP-based communication\r\nAbility to integrate new tools into existing infrastructures\r\nFamiliarity with how LLM agents are prompted, executed, and evaluated\r\nClear documentation and communication skills – you'll work with QA and writers\r\nWe also value applicants who have\r\nExperience with Model Context Protocol (MCP) or similar structured agent-server interfaces\r\nKnowledge of FastAPI or similar async web frameworks\r\nExperience working with LLM logs, scoring functions, or sandbox environments\r\nAbility to support dev environments (devcontainers, CI configs, linters)\r\nJS experience\r\nBenefits\r\nGet paid for your expertise, with rates that can go up to $80/hour depending on your skills, experience, and project needs\r\nTake part in a flexible, remote, freelance project that fits around your primary professional or academic commitments\r\nParticipate in an advanced AI project and gain valuable experience to enhance your portfolio\r\nInfluence how future AI models understand and communicate in your field of expertise\r\nOther Information\r\nSeniority level: Mid-Senior level\r\nEmployment type: Part-time\r\nJob function: Other\r\nIndustries: IT Services and IT Consulting\r\nReferrals increase your chances of interviewing at Mindrift by 2x.\r\nLocation: Missouri, United States (remote)\r\nPay range: $20.00-$40.00 per hour (freelance project)\r\nNote: We're open to applicants from selected countries; please check eligibility.\r\nJ-18808-Ljbffr","company":"Mind Rift","rawCompany":"mind rift","city":"Burlington","state":"IA","isRemote":false,"isActive":false,"createdAt":"2026-04-10T04:52:52.562Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1254.00","title":"Web Developers","slug":"web-developers"},{"code":"15-1299.04","title":"Penetration Testers","slug":"penetration-testers"}],"industries":[{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"MCP & Tools Python Developer - Agent Evaluation Infrastructure","description":"This opportunity is only for candidates currently residing in the specified country. Your location may affect eligibility and rates. Please submit your resume in English and indicate your level of English proficiency.\r\nAt Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of AI.\r\nWhat We Do\r\nThe Mindrift platform, launched and powered by Toloka, connects domain experts with cutting-edge AI projects from innovative tech clients. Our mission is to unlock the potential of GenAI by tapping into real-world expertise from across the globe.\r\nWho We're Looking For\r\nCalling all security researchers, engineers, and penetration testers with a strong foundation in problem-solving, offensive security, and AI-related risk assessment. If you thrive on digging into complex systems, uncovering hidden vulnerabilities, and thinking creatively under constraints, join us! We're looking for someone who can bring a hands-on approach to technical challenges, whether breaking into systems to expose weaknesses or building secure tools and processes. We value contributors with a passion for continuous learning, experimentation, and adaptability.\r\nAbout the Project\r\nWe're on the hunt for hands-on Python engineers for a new project focused on developing Model Context Protocol (MCP) servers and internal tools for running and evaluating agent behavior. You'll implement base methods for agent action verification, integrate with internal and client infrastructures, and help fill tooling gaps across the team.\r\nWhat You'll Be Doing\r\nDeveloping and maintaining MCP-compatible evaluation servers\r\nImplementing logic to check agent actions against scenario definitions\r\nCreating or extending tools that writers and QAs use to test agents\r\nWorking closely with infrastructure engineers to ensure compatibility\r\nOccasionally helping with test writing or debug sessions when needed\r\nAlthough we're only looking for experts for this current project, contributors with consistent high-quality submissions may receive an invitation for ongoing collaboration across future projects.\r\nHow to Get Started\r\nApply to this post, qualify, and get the chance to contribute to a project aligned with your skills, on your own schedule. Shape the future of AI while building tools that benefit everyone.\r\nRequirements\r\nThe ideal contributor will have\r\n4+ years of Python development experience, ideally in backend or tools\r\nSolid experience building APIs, testing frameworks, or protocol-based interfaces\r\nUnderstanding of Docker, Linux CLI, and HTTP-based communication\r\nAbility to integrate new tools into existing infrastructures\r\nFamiliarity with how LLM agents are prompted, executed, and evaluated\r\nClear documentation and communication skills – you'll work with QA and writers\r\nWe also value applicants who have\r\nExperience with Model Context Protocol (MCP) or similar structured agent-server interfaces\r\nKnowledge of FastAPI or similar async web frameworks\r\nExperience working with LLM logs, scoring functions, or sandbox environments\r\nAbility to support dev environments (devcontainers, CI configs, linters)\r\nJS experience\r\nBenefits\r\nGet paid for your expertise, with rates that can go up to $80/hour depending on your skills, experience, and project needs\r\nTake part in a flexible, remote, freelance project that fits around your primary professional or academic commitments\r\nParticipate in an advanced AI project and gain valuable experience to enhance your portfolio\r\nInfluence how future AI models understand and communicate in your field of expertise\r\nOther Information\r\nSeniority level: Mid-Senior level\r\nEmployment type: Part-time\r\nJob function: Other\r\nIndustries: IT Services and IT Consulting\r\nReferrals increase your chances of interviewing at Mindrift by 2x.\r\nLocation: Missouri, United States (remote)\r\nPay range: $20.00-$40.00 per hour (freelance project)\r\nNote: We're open to applicants from selected countries; please check eligibility.\r\nJ-18808-Ljbffr","datePosted":"2026-04-10T04:52:52.562Z","dateModified":"2026-04-10T04:52:52.562Z","hiringOrganization":{"@type":"Organization","name":"Mind Rift","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Burlington","addressRegion":"IA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"2005dd8cc030930fd12b5b69"},"url":"https://jobsearcher.com/jobs/2005dd8cc030930fd12b5b69"}}