pPlease submit your CV in English and indicate your level of English proficiency. /p pMindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. bParticipation is project-based, not permanent employment. /b /p pWe're building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks. /p pYou’ll create challenging tasks and evaluation criteria within realistic simulated environments: /p ul liBuild realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history /li liDesign tasks from intermediate states of these environments - craft the prompt, define what "solved" means, and ensure the task is solvable by an AI agent /li liWrite tests that verify agent solutions - accept all valid approaches and reject incorrect ones, neither too strict nor too lenient /li liIterate on tasks and tests based on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robust /li /ul h3What this is NOT: /h3 ul liNot data labeling /li liNot prompt engineering /li liNot writing code from scratch - the agent writes most of the code; you guide and evaluate /li /ul h3What we look for: /h3 ul li5+ years in software development /li liCore stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis /li liExperience writing tests (functional, integration) /li liEnglish proficiency - B2+ /li /ul h3Why this is hard: /h3 pFrontier 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. /p h3Requirements and benefits /h3 h3Educational qualifications /h3 ul liA Master’s Degree in Computer Science, Software Engineering, Data Science / Data Analytics, Artificial Intelligence / Machine Learning, Computational Linguistics / Natural Language Processing (NLP), Information Systems or other related fields. /li liBachelor’s degree is accepted if only candidate has 5 years of experience in the field. /li /ul h3Academic and/or Professional Experience /h3 pCandidates should have a minimum of 3 years of professional experience in related roles or domain - specifically for QA-automation/testing or cybersecurity roles. /p h3How it works /h3 pApply → Pass qualification(s) → Join a project → Complete tasks → Get paid /p h3Compensation: /h3 pPaid per accepted task. Your rate depends on the qualification tier you reach and how efficiently you complete tasks - up to the equivalent of b$40/hr /b. Because payment is per task, a faster pace raises your effective hourly rate. /p h3Why this freelance opportunity might be a great fit for you? /h3 ul liTake part in a tempo parziale, remote, freelance project that fits around your primary professional or academic commitments. /li liWork on advanced AI projects and gain valuable experience that enhances your portfolio. - Influence how future AI models understand and communicate in your field of expertise. /li /ul #J-18808-Ljbffr

📌 Freelance Agent Evaluation Engineer (Italia)
🏢 Mindrift
📍 Italia