Evaluation Scenario Writer

Overview2 days ago Be among the first 25 applicantsAt Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of AI. The 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.Who we're looking for: We're looking for curious and intellectually proactive contributors who never miss an error and can think outside of the box when brainstorming solutions. Are you comfortable with ambiguity and complexity? Does an async, remote, flexible opportunity sound exciting? Would you like to learn how modern AI systems are tested and evaluated?This is a flexible, project-based opportunity well-suited for:Analysts, researchers, or consultants with strong critical thinking skillsStudents (senior undergrads / grad students) looking for an intellectually interesting gigPeople open to a part-time and non-permanent opportunityAbout the project: We're on the hunt for an Evaluation Scenario Writer - QA for a new project focused on ensuring the quality and correctness of evaluation scenarios created for LLM agents. This project opportunity blends manual scenario validation, automated test thinking, and collaboration with writers and engineers. You will verify test logic, flag inconsistencies, and help maintain a high bar for evaluation coverage and clarity.What you'll be doingReviewing and validating test scenarios from Evaluation WritersSpotting logical inconsistencies, ambiguities, or missing checksSuggesting improvements to structure, edge cases, or scoring logicCollaborating with infrastructure and tool developers to automate parts of the reviewCreating clean and testable examples for others to followAlthough 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.How To Get StartedApply 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.RequirementsThe ideal contributor will have:Strong QA background (manual or automation), preferably in complex testing environmentsUnderstanding of test design, regression testing, and edge case detectionAbility to evaluate logic and structure of test scenarios (even if written by others)Experience reviewing and debugging structured test case formats (JSON, YAML)Familiarity with Python and JS scripting for test automation or validationClear communication and documentation skillsWillingness to occasionally write or refactor test scenariosWe also value applicants who have:Experience testing AI-based systems or NLP applicationsFamiliarity with scoring systems and behavioral evaluationGit/GitHub workflow familiarity (PR review, versioning of test cases)Experience using test management systems or tracking toolsBenefitsContribute on your own schedule, from anywhere in the world. This opportunity allows you to get paid for your expertise, with rates that can go up to $47/hour depending on your skills, experience, and project needsTake part in a flexible, remote, freelance project that fits around your primary professional or academic commitmentsParticipate in an advanced AI project and gain valuable experience to enhance your portfolioInfluence how future AI models understand and communicate in your field of expertiseJob DetailsSeniority level: InternshipEmployment type: Part-timeJob function: OtherIndustries: IT Services and IT ConsultingReferrals increase your chances of interviewing at Mindrift by 2xGet notified about new Writer jobs in France. #J-18808-Ljbffr