As a Software Engineering evaluator, you will create datasets for training, benchmarking, and advancing large language models in close collaboration with researchers. You will curate code examples, provide solutions, and correct 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 work with cross-functional teams to improve enterprise-level AI-driven coding solutions. The work also includes building agents to verify code quality and identify error patterns; evaluating model capabilities across stages of the software engineering lifecycle, from prototyping and architecture/API design through implementation, launch, experimentation, monitoring, and operational maintenance; and designing mechanisms to automatically verify solutions to software engineering tasks. This is a contractor engagement requiring a flexible commitment of at least 10 hours per week and up to 40 hours per week. The initial duration is one month, with potential 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 completion of 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