Evaluation Scenario Writer - AI Agent Testing Specialist
Posted 1 month ago Expired
This job has expired
Looking for a job like Evaluation Scenario Writer - AI Agent Testing Specialist? Upload your resume and we'll notify you when similar positions become available.
Upload Your ResumeAbout This Role
Create challenging and realistic coding test cases to evaluate and improve AI coding systems' capabilities. Focus on designing comprehensive functional tests that validate end-to-end behavior and analyze AI failures to understand model strengths and weaknesses.
Responsibilities
- Review and refine realistic coding tasks based on provided production codebases
- Write comprehensive functional tests that validate actual end-to-end behavior and edge-cases
- Craft "fair but hard" challenges for AI systems, requiring complex reasoning and information retrieval across scattered data
- Analyze AI failures to understand model struggles versus mastery
- Iterate based on feedback from expert QA reviewers
Requirements
- Degree in Computer Science, Software Engineering or related fields
- 5+ years in software development, primarily Python (pytest, async/await, subprocess, file operations)
- Background in Full-Stack development (React-based interfaces and robust Back-end systems)
- Experience writing tests (functional, integration)
- Docker containers (running evaluations locally in containers)
- CI/CD understanding (GitHub Actions as a user: triggers, labels, reading results)
- English proficiency - B2
Qualifications
- Degree in Computer Science, Software Engineering or related fields
- 5+ years in software development, primarily Python
Skills
* Required skills
About Mindrift
Mindrift connects specialists with AI projects from major tech innovators, unlocking the potential of Generative AI by tapping into real-world expertise from across the globe.