{"schemaVersion":"jobsearcher.job.v1","id":"dbb65c89c6bd4c811460a296","url":"https://jobsearcher.com/jobs/dbb65c89c6bd4c811460a296","canonicalUrl":"https://jobsearcher.com/jobs/dbb65c89c6bd4c811460a296","title":"Senior Software Engineer (Python) - Agent Evaluation - Freelance/Remote 100+ openings","description":"This opportunity is intended for experienced Senior Python Engineers only****Open to candidates in the North America, South America, Asia and Europe.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 InvolvesWe'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 for - You must meet all the requirements in order to be considered for this project:5+ years of professional experience with Python.Strong experience with FastAPI, pytest, and async/await.Hands-on experience with Docker, PostgreSQL, and CI/CD pipelines.Proven experience writing and maintaining automated tests (not just executing them).Full-stack experience with React and TypeScript is a plus.English proficiency at B2 level or higher.Availability to work 30+ hours per week.Why this is hard Frontier 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 paidHiring & Onboarding ProcessThe process is designed to move quickly and typically includes the following steps:App review and invitation to a virtual project introduction session (approximately 30 minutes)Platform registration and identity verificationTechnical assessment (approximately 35 minutes)Background check (completed at no cost to candidates)Onboarding and project-specific training tasksBegin production work!Additional RequirementsWillingness to complete identity verification as part of the onboarding process.Ability to complete a technical assessment.Willingness to join and participate in Discord, which will be used for project communication and updates.Successful completion of a background check is required prior to onboarding.Reliable internet connection and ability to communicate effectively in a remote environment.","company":"Braintrust","rawCompany":"braintrust","isRemote":true,"isActive":false,"createdAt":"2026-07-03T11:02:59.223Z","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 (Python) - Agent Evaluation - Freelance/Remote 100+ openings","description":"This opportunity is intended for experienced Senior Python Engineers only****Open to candidates in the North America, South America, Asia and Europe.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 InvolvesWe'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 for - You must meet all the requirements in order to be considered for this project:5+ years of professional experience with Python.Strong experience with FastAPI, pytest, and async/await.Hands-on experience with Docker, PostgreSQL, and CI/CD pipelines.Proven experience writing and maintaining automated tests (not just executing them).Full-stack experience with React and TypeScript is a plus.English proficiency at B2 level or higher.Availability to work 30+ hours per week.Why this is hard Frontier 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 paidHiring & Onboarding ProcessThe process is designed to move quickly and typically includes the following steps:App review and invitation to a virtual project introduction session (approximately 30 minutes)Platform registration and identity verificationTechnical assessment (approximately 35 minutes)Background check (completed at no cost to candidates)Onboarding and project-specific training tasksBegin production work!Additional RequirementsWillingness to complete identity verification as part of the onboarding process.Ability to complete a technical assessment.Willingness to join and participate in Discord, which will be used for project communication and updates.Successful completion of a background check is required prior to onboarding.Reliable internet connection and ability to communicate effectively in a remote environment.","datePosted":"2026-07-03T11:02:59.223Z","dateModified":"2026-07-03T11:02:59.223Z","hiringOrganization":{"@type":"Organization","name":"Braintrust","sameAs":"https://jobsearcher.com"},"jobLocationType":"TELECOMMUTE","applicantLocationRequirements":{"@type":"Country","name":"US"},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"dbb65c89c6bd4c811460a296"},"url":"https://jobsearcher.com/jobs/dbb65c89c6bd4c811460a296"}}