{"schemaVersion":"jobsearcher.job.v1","id":"234f55801acaffe0c319a795","url":"https://jobsearcher.com/jobs/234f55801acaffe0c319a795","canonicalUrl":"https://jobsearcher.com/jobs/234f55801acaffe0c319a795","title":"AI Evaluation Engineer (Python, QA or Security)","description":"Please submit your CV in English and indicate your level of English proficiency.Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment.What this opportunity involves We're building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks.You'll create challenging tasks and evaluation criteria within realistic simulated environments:Build realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development historyDesign tasks from intermediate states of these environments - craft the prompt, define what \"solved\" means, and ensure the task is solvable by an AI agentWrite tests that verify agent solutions - accept all valid approaches and reject incorrect ones, neither too strict nor too lenientIterate on tasks and tests based on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robustWhat this is NOTNot data labelingNot prompt engineeringNot writing code from scratch - the agent writes most of the code; you guide and evaluateWhat we look for5+ years in software developmentCore stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, RedisExperience writing tests (functional, integration)English proficiency - B2+Why this is hardFrontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. You need to deeply understand where models fail and what scenarios reveal the difference between a good and a bad solution. Tasks have many valid solutions - writing tests that accept all correct solutions and reject incorrect ones is harder than it sounds.How it worksApply ? Pass qualification(s) ? Join a project ? Complete tasks ? Get paidCompensationUp to $50/hr equivalent , depending on level and pace. Tasks are estimated at ~20 hours each; you set your own schedule.Originally posted on Himalayas","company":"Gigfinderai","rawCompany":"gigfinderai","city":"South Bend","state":"IN","isRemote":false,"isActive":false,"createdAt":"2026-08-23T08:28:58.833Z","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":"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":"AI Evaluation Engineer (Python, QA or Security)","description":"Please submit your CV in English and indicate your level of English proficiency.Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment.What this opportunity involves We're building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks.You'll create challenging tasks and evaluation criteria within realistic simulated environments:Build realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development historyDesign tasks from intermediate states of these environments - craft the prompt, define what \"solved\" means, and ensure the task is solvable by an AI agentWrite tests that verify agent solutions - accept all valid approaches and reject incorrect ones, neither too strict nor too lenientIterate on tasks and tests based on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robustWhat this is NOTNot data labelingNot prompt engineeringNot writing code from scratch - the agent writes most of the code; you guide and evaluateWhat we look for5+ years in software developmentCore stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, RedisExperience writing tests (functional, integration)English proficiency - B2+Why this is hardFrontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. You need to deeply understand where models fail and what scenarios reveal the difference between a good and a bad solution. Tasks have many valid solutions - writing tests that accept all correct solutions and reject incorrect ones is harder than it sounds.How it worksApply ? Pass qualification(s) ? Join a project ? Complete tasks ? Get paidCompensationUp to $50/hr equivalent , depending on level and pace. Tasks are estimated at ~20 hours each; you set your own schedule.Originally posted on Himalayas","datePosted":"2026-08-23T08:28:58.833Z","dateModified":"2026-08-23T08:28:58.833Z","hiringOrganization":{"@type":"Organization","name":"Gigfinderai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"South Bend","addressRegion":"IN","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"234f55801acaffe0c319a795"},"url":"https://jobsearcher.com/jobs/234f55801acaffe0c319a795"}}