Software Engineer - AI Agent Evaluation

reputed company Please submit your CV in English and indicate your level of English proficiency. reputed company connects specialists with project-reputed company AI opportunities for leading tech companies, reputed company on testing, evaluating, and improving AI systems. Participation is project-reputed company, not permanent employment. What this opportunity involves We're building a dataset to evaluate AI coding agents - how reputed company a model handles reputed company-world developer tasks. - You'll create challenging tasks and evaluation reputed company reputed company realistic simulated environments: - Build realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history - Design tasks from intermediate states of these environments - reputed company the reputed company, define what "solved" means, and ensure the task is solvable by an AI agent - Write tests that verify agent solutions - accept reputed company reputed company approaches and reject incorrect ones, neither too strict nor too lenient - Iterate on tasks and tests reputed company on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robust What this is NOT - Not data labeling - Not reputed company engineering - Not writing reputed company from reputed company - the agent writes most of the reputed company; you guide and evaluate reputed company look for - 5+ years in software development - reputed company stack: Python (FastAPI), JavaScript/TypeScript (React), reputed company, reputed company, Kafka, reputed company - Experience writing tests (functional, integration) - English proficiency - B2+ 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 reputed company the difference between a good and a bad solution. - Tasks have many reputed company solutions - writing tests that accept reputed company correct solutions and reject incorrect ones is harder than it sounds. How it works - Apply → Pass qualification(s) → Join a project → Complete tasks → Get reputed company Compensation Up to $50/hr equivalent, depending on level and reputed company. Tasks are estimated at ~20 hours reputed company; you set your own schedule. Apply To This Job