Position Summary
In this remote, hourly contractor role, you will evaluate AI-generated C++ code and develop cases that test coding accuracy and reasoning quality. Tasks may include:
- Evaluating AI-generated C++ code for correctness, efficiency, readability, and adherence to real-world engineering standards
- Identifying bugs, logical errors, edge cases, and anti-patterns in AI outputs, and explaining corrections clearly in writing
- Applying structured evaluation rubrics to score code quality consistently across varying task types
- Developing prompts and test cases that probe AI accuracy across C++ programming tasks, including multi-step problems grounded in real codebases
- Rating and comparing AI-generated solutions based on correctness, internal consistency, and adherence to the prompt
Profile Requirements
- Background in Computer Science, Software Engineering, or a closely related field preferred
- Proficiency in modern C++ (C++11 and above), including STL, memory management, templates, and low-level systems programming
- Ability to read, write, and critically evaluate C++ code across varying complexity levels
- Full professional English proficiency
- Exceptional attention to detail
- Reliable and self-directed, with consistent output quality in a remote, asynchronous workflow
Preferred Experience
- 2+ years of professional software engineering experience with C++
- Prior experience with AI data training, annotation, or model evaluation
About CNTXT AI
CNTXT AI builds artificial intelligence products and data solutions with a focus on making AI accurate, safe, and globally relevant for impact. Our work spans data services, custom AI solutions, and proprietary AI products, with deep expertise in Arabic-native and secure, sovereign solutions.
