Freelance AI Evaluation Engineer (Python/Full-Stack) (Hyderabad)

You will be connecting specialists with project-based AI opportunities for leading tech companies through Mindrift. The focus will be on testing, evaluating, and improving AI systems. Participation in projects is on a project-based basis, not as permanent employment. Key Responsibilities: - Review and refine realistic coding tasks based on provided production codebases with realistic scope, requirements, and information sources - Write comprehensive functional tests that validate actual end-to-end behavior and edge-cases, not just superficial checks - Craft "fair but hard" challenges where the AI has all the context it needs, but has to work for it (information scattered across files and external sources, complex reasoning required) - Analyze AI failures to understand what the model struggles with versus what it masters - Iterate based on feedback from expert QA reviewers who score your work on 7 quality criteria Qualifications Required: - Degree in Computer Science, Software Engineering, or related fields - 5+ years in software development, primarily in Python (pytest, async/await, subprocess, file operations) - Background in Full-Stack development, with an equal focus on building React-based interfaces and robust Back-end systems - Experience writing tests (functional, integration not just running them) - Familiarity with Docker containers (running evaluations locally in containers) - Understanding of CI/CD (GitHub Actions as a user: triggers, labels, reading results) - English proficiency at level B2 This opportunity is suitable for experienced developers, software engineers, and test automation specialists who are open to part-time, non-permanent projects. The compensation for this project can go up to $12 per hour equivalent, depending on the level and pace of your contribution. The effort estimate for tasks in this project is approximately 20 hours, depending on complexity. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted. Please note that compensation may vary across projects based on scope, complexity, and required expertise. Keep in mind that other projects on the platform may offer different earning levels based on their specific requirements. You will be connecting specialists with project-based AI opportunities for leading tech companies through Mindrift. The focus will be on testing, evaluating, and improving AI systems. Participation in projects is on a project-based basis, not as permanent employment. Key Responsibilities: - Review and refine realistic coding tasks based on provided production codebases with realistic scope, requirements, and information sources - Write comprehensive functional tests that validate actual end-to-end behavior and edge-cases, not just superficial checks - Craft "fair but hard" challenges where the AI has all the context it needs, but has to work for it (information scattered across files and external sources, complex reasoning required) - Analyze AI failures to understand what the model struggles with versus what it masters - Iterate based on feedback from expert QA reviewers who score your work on 7 quality criteria Qualifications Required: - Degree in Computer Science, Software Engineering, or related fields - 5+ years in software development, primarily in Python (pytest, async/await, subprocess, file operations) - Background in Full-Stack development, with an equal focus on building React-based interfaces and robust Back-end systems - Experience writing tests (functional, integration not just running them) - Familiarity with Docker containers (running evaluations locally in containers) - Understanding of CI/CD (GitHub Actions as a user: triggers, labels, reading results) - English proficiency at level B2 This opportunity is suitable for experienced developers, software engineers, and test automation specialists who are open to part-time, non-permanent projects. The compensation for this project can go up to $12 per hour equivalent, depending on the level and pace of your contribution. The effort estimate for tasks in this project is approximately 20 hours, depending on complexity. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted. Please note that compensation may vary across projects based on scope, complexity, and required expertise. Keep in mind that other projects on the platform may offer different earning levels based on their specific requirements.