20 hours ago
Remote, Poland +4 moreSenior
Responsibilities
- Build realistic simulated developer environments containing codebases, infrastructure, tickets, documentation, conversations, and development history.
- Design challenging tasks from intermediate environment states, including prompts, success criteria, and solvability requirements.
- Write functional and integration tests that correctly accept valid AI-agent solutions and reject incorrect ones.
- Review agent solutions, analyze failures, and iterate on tasks and tests using QA feedback.
- Create evaluation datasets for assessing AI coding agents on real-world developer tasks.
Requirements
- At least 5 years of software development experience.
- Experience writing functional and integration tests.
- Proficiency with Python and FastAPI, JavaScript or TypeScript and React, Docker, Postgres, Kafka, and Redis.
- English proficiency at B2 level or higher.
- A Master's degree in Computer Science, Software Engineering, Data Science or Data Analytics, Artificial Intelligence or Machine Learning, Computational Linguistics or NLP, Information Systems, or a related field.
- A bachelor's degree is accepted with 5 years of experience in the field.
- At least 3 years of professional experience in related roles or domains is specified for QA-automation/testing or cybersecurity roles.
Benefits
- Remote, part-time freelance work that can fit around other professional or academic commitments.
- Project-based participation with the opportunity to work on advanced AI projects and enhance a portfolio.
- Opportunity to influence how future AI models understand and communicate in the field.
- Payment is per accepted task, with the rate depending on qualification tier and task efficiency.
- Participation is project-based rather than permanent employment.
Tech Stack
Categories
About Mindrift
Mindrift builds an expert-sourcing platform that connects domain specialists to project-based work training and evaluating generative AI models, including supervised fine-tuning, RLHF, evaluation, and red-teaming. It is built and operated by Toloka, part of Nebius Group, and run from Amsterdam, Netherlands. Work is fully remote and freelance, serving global technology companies developing and improving large AI systems.