About the job
We invite you to submit your CV in English, alongside your level of English proficiency.
At Mindrift, we bridge the gap between talented specialists and project-oriented AI opportunities within leading technology companies, emphasizing the rigorous testing, evaluation, and enhancement of AI systems. Please note that participation is project-based rather than permanent employment.
About the Role
In this role, you will develop complex coding test scenarios that challenge AI coding systems to excel:
- Evaluate and enhance realistic coding tasks using provided production codebases, ensuring they encompass practical scope, requirements, and comprehensive information sources.
- Create in-depth functional tests that assess true end-to-end behavior and edge cases, moving beyond superficial evaluations.
- Design “fair yet challenging” tasks where the AI is provided with all necessary context but must engage in thorough analysis (information distributed across files and external sources, requiring intricate reasoning).
- Examine AI failures to discern the model's weaknesses compared to its strengths.
- Refine your work based on feedback from expert QA reviewers who assess your contributions against 7 quality metrics.
Ideal Candidate Profile
This opportunity is ideal for seasoned developers, software engineers, and test automation specialists who are open to part-time, non-permanent projects. The perfect candidate will possess:
- A degree in Computer Science, Software Engineering, or a related discipline.
- Over 5 years of experience in software development, with a strong emphasis on Python (pytest, async/await, subprocess, file operations).
- A robust background in Full-Stack development, equally focusing on creating React-based interfaces and resilient back-end systems.
- Proficiency in writing tests (functional, integration – not merely executing them).
- Experience with Docker containers (running assessments locally within containers).
- Understanding of CI/CD processes (specifically GitHub Actions as an end-user: triggers, labels, interpreting results).
- A minimum English proficiency level of B2.
How to Get Involved
Simply apply → Pass qualifications → Join a project → Complete assigned tasks → Receive payment.
Estimated Effort
Tasks for this project are anticipated to take approximately 20 hours to complete, contingent on complexity. While this is an estimate, you have the flexibility to choose your working hours and methodology. All tasks must be submitted by the deadline and adhere to the specified acceptance criteria to be approved.
Compensation
- Competitive compensation for contributions, with rates up to $12/hour*.
- Fixed project rates or individual rates, depending on the project specifics.
- Some projects may include additional incentive payments.
*Note: Rates are subject to variation based on expertise, skills assessment, location, project requirements, and other factors. Higher rates may be available for highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are provided per project.

