Software Engineer, AI Code Evaluation & Benchmarking (US candidates only)
- Contract: Full time
- Who can apply: United States
- Posted Jun 12, 2026
In short
Do you want to work remotely as a Software Engineer, AI Code Evaluation & Benchmarking (US candidates only)? Through Turing, you will help improve advanced AI coding systems by reviewing code and creating benchmarks. This full-time contractor role suits engineers who want flexible remote work.
What you will do
- Review and evaluate AI-generated code for correctness and efficiency.
- Analyze software engineering tasks and validate proposed solutions.
- Debug code, reproduce issues, and verify fixes across environments.
- Create and maintain evaluation datasets and grading rubrics.
What you need to apply
- Hold a Bachelor's or Master's degree in Computer Science or a related technical field.
- Have at least 3 years of professional software engineering experience.
- Demonstrate strong proficiency in languages like Python, Java, C/C++, Go, Swift, Objective-C, PHP, or SQL.
- Show experience performing code reviews and evaluating code quality.
Who can apply
This full-time contractor assignment is open exclusively to residents of the US.
My tip
At Simply Remotely, we advise you to highlight your coding proficiency and code review experience clearly when applying.