Freelance AI Evaluation Engineer

Mindrift offers project-based AI opportunities with leading tech companies, focusing on testing, evaluating, and improving AI systems. This is a project-based role, not permanent employment.

What This Opportunity Involves:

You will develop rigorous coding test cases to challenge AI coding systems. This includes reviewing and refining realistic coding tasks based on provided production codebases, writing comprehensive functional tests for end-to-end behavior and edge cases, and crafting challenging scenarios that require complex reasoning. You'll analyze AI failures to understand model limitations and iterate based on feedback from expert QA reviewers.

What We Look For:

This opportunity is suited for experienced developers, software engineers, and test automation specialists seeking part-time, non-permanent projects. Ideal candidates will have a degree in Computer Science, Software Engineering, or a related field, with over 5 years of experience in software development, particularly in Python (pytest, async/await, subprocess, file operations). Experience in Full-Stack development, including React-based interfaces and back-end systems, is highly valued. Proficiency in writing tests (functional, integration), Docker containers, and CI/CD understanding (GitHub Actions) is expected. A B2 level of English proficiency is required.

How It Works:

Apply, pass qualifications, join a project, complete tasks, and get paid. Tasks are estimated to take 20 hours, with flexible working hours. Deadlines and acceptance criteria must be met for task completion.

Compensation:

Earn up to $12 per hour equivalent, with compensation varying based on project scope, complexity, and required expertise.