As a Software Engineering evaluator, you will create datasets to train, benchmark, and advance large language models in close collaboration with researchers. The work includes curating code examples, providing solutions, and correcting code primarily in C/C++, as well as Python, JavaScript (including ReactJS), Java, Rust, and Go. You will evaluate and refine AI-generated code for efficiency, scalability, and reliability, and collaborate with cross-functional teams to improve enterprise-level AI coding solutions. The role also involves building agents to verify code quality and identify error patterns, evaluating model capabilities across stages of the software engineering cycle, and designing mechanisms to automatically verify solutions to software engineering tasks. This is a flexible contractor engagement of at least 10 hours and up to 40 hours per week, initially lasting one month, with possible extensions based on performance and fit. Candidates must be based in the US, Canada, or specified Western European countries. The application process takes 15–30 minutes and requires an AI video interview.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Career Level
Mid Level
Education Level
No Education Listed