Evaluate AI-generated software with Python, C/C++, Rust, and Go expertise. This versatile contractor engagement is open to United States-based candidates.
As a Software Engineering evaluator at Turing, you will create datasets for training and benchmarking large language models. You will curate code examples, provide precise solutions, and correct code across multiple languages. The work emphasizes systems-level correctness, performance-critical applications, infrastructure, and reliability.
Key Responsibilities:
- Curate code examples for AI model training initiatives
- Evaluate AI-generated code for performance and reliability
- Build agents verifying systems-level and infrastructure code
- Design mechanisms that automatically verify software solutions
- Collaborate on AI-driven coding solutions against benchmarks
Requirements:
- Three or more years of software engineering experience
- Expertise in systems programming, infrastructure, or backend development
- Experience deploying scalable, production-grade software
- Understanding of architecture, debugging, and code quality assessment
- Excellent oral and written communication skills
Apply software engineering judgment across AI evaluation, systems programming, infrastructure code, and scalable production software at Turing.