Remote Python AI Engineer - Data & Model Evaluation

Turing, based in San Francisco, seeks a Software Engineering evaluator to curate coding datasets and assess AI-generated code across Python and other languages. You will work with researchers to improve benchmarks and production-grade pipelines while focusing on scalability, reliability, and maintainability.

The role emphasizes collaboration with cross-functional teams and clear technical rationales, with a flexible contractor engagement and 10–40 hours per week.