# Model Evaluator

Model evaluation (RLHF) · Remote, Mexico · Freelance

- **Typical project pay**: MXN 120-180 per hour
- **Where**: Remote, Mexico
- **Contract**: Freelance
- **Status**: Applications open
- **Published**: 2026-09-23

Each project invitation states the work, your pay, what the pay covers and what the work must meet. You see it before you accept.

Rate and compare AI answers and explain why, as paid work from home. It suits careful readers who can say why an answer is wrong, not only that it is.

### What the work is for

Your ratings and written reasons help train AI models and test their answers.

### The work

- Rate and compare AI answers against the project's criteria.
- Write a short, concrete reason for each rating. It matters as much as the rating itself.
- Check the facts in an answer. Rewrite weak answers where the task asks for it.
- Flag unsafe, false or policy-breaking output explicitly.

### What to expect

- Each project has its own rating criteria and instructions for judging answers.
- You work in YPAI's own review console, where each project's rating criteria are set up.

### You need

- Strong reading comprehension in the language you evaluate.
- The ability to explain why, not only what.
- 18 years or older.

### Good to know

- You will read unsafe or offensive output at times. Judging it is part of the work.
- Work depends on the projects running in the language you evaluate. There can be gaps between projects.

Our team reviews applications for this role and contacts selected applicants by email.

## Apply

Takes a couple of minutes. No CV needed.

- **Payment**: Via PayPal, Wise, or bank transfer
- **When you are paid**: Paid every two weeks after approved work.
- **Fees to you**: Never, at any stage. If someone asks, it is not us
- **Who hires you**: YPAI, a registered Norwegian company that collects and annotates data for AI

[Apply now](https://freelancer.ypai.ai/jobs/openings/model-evaluator-mx)