Evaluate AI-generated C++ code and develop cases that test coding accuracy and reasoning quality.
- Assess code correctness, efficiency, readability, and adherence to engineering standards.
- Identify bugs, logical errors, edge cases, and anti-patterns, and explain corrections clearly in writing.
- Apply structured rubrics to score code quality consistently.
- Develop prompts and test cases for C++ programming tasks, including multi-step problems grounded in real codebases.
- Rate and compare AI-generated solutions for correctness, consistency, and adherence to prompts.
Requirements: Background in Computer Science, Software Engineering, or a related field preferred; proficiency in modern C++ (C++11 and above), including STL, memory management, templates, and low-level systems programming; ability to evaluate C++ code across varying complexity; full professional English proficiency; attention to detail; self-direction and reliable output in a remote, asynchronous workflow.
Preferred experience: 2+ years of professional C++ software engineering experience; prior experience in AI data training, annotation, or model evaluation.
Conditions: Remote, hourly contractor role.