Senior Python Engineer, LLM Code Evaluation

You will evaluate AI-generated code and programming materials for an LLM evaluation project. You will use project guidelines to make careful judgments and give clear feedback.

• Review source materials and model outputs against project guidelines.
• Assess code quality and document evidence for your judgments.
• Explain your evaluations clearly so the feedback can help improve model behavior.
• Keep your reviews consistent and accurate across repeated tasks.

What it pays and takes

• Pay: Compensation is handled through the project budget fields on the job page.
• Schedule: 20 or more hours per week, with the opportunity to work up to 40 hours per week.
• Location: Open to candidates in the United States.
• Language: Fluent in English, with strong written and spoken communication skills.
• Skills: Strong Python expertise, including frameworks, tools, and practices for building production software.
• Skills: Experience building full-stack applications and deploying scalable software.
• Skills: Deep knowledge of software architecture, design, development, debugging, code quality, and code review.
• Helpful background: Computer science graduates from Stanford, MIT, Carnegie Mellon, UC Berkeley, Georgia Tech, or comparable schools are welcome. Strong experience and skill matter more than school.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training uses examples and human reviews to help AI systems learn. Experienced engineers are paid to apply their software expertise and explain judgments that can help improve model outputs.