Use Python and full-stack engineering expertise remotely to evaluate code for Turing’s large language model training initiatives.
As a Software Engineering evaluator, you will create datasets, provide accurate solutions, and correct code for AI research. The work emphasizes Python across backend services, data pipelines, and machine learning infrastructure. You will also work with JavaScript, ReactJS, C/C++, Java, Rust, and Go while assessing production-grade software quality.
Key Responsibilities
Curate code examples for training and benchmarking language models
Evaluate AI-generated code for efficiency, scalability, and reliability
Build Python agents and automated verification tools
Design mechanisms that verify software engineering solutions automatically
Collaborate with cross-functional teams on AI-driven coding solutions
Requirements
Three or more years of software engineering experience
Strong Python expertise, frameworks, tooling, and best practices
Full-stack application development and scalable software deployment experience
Deep software architecture, debugging, and code quality understanding
Clear oral and written communication for evaluation rationales
Apply full-stack engineering, Python, and code evaluation expertise to advance reliable AI-driven software systems with Turing.