Remote AI Evaluation Engineer Creating Challenging Coding Tests

About

Drive innovation by developing cutting-edge coding challenges as an AI Evaluation Engineer. Utilize your advanced skills in Python and test automation to evaluate AI systems effectively.
This project-based role is ideal for seasoned developers or software engineers with a strong background in test automation. You'll have the opportunity to create realistic coding tasks, validate AI's end-to-end functionality, and analyze AI behaviors. Your expertise in full-stack development, particularly with React and back-end systems, will be crucial.

Responsibilities

• Design and refine coding test cases from production codebases
• Write comprehensive functional tests validating real-world scenarios
• Create challenging tasks requiring complex reasoning
• Analyze AI failures and evolution for improvement
• Iterate based on feedback from QA reviewers

Requirements

• 5+ years of software development experience
• Strong skills in Python, including pytest and async/await
• Experience in full-stack development with React
• Familiarity with Docker and CI/CD processes
• English proficiency at B2 level

Additional Information

Leverage your software development expertise to challenge and enhance AI systems while enjoying the flexibility of part-time project work.
#J-18808-Ljbffr