Judging

Local Search Quality Evaluator

Evaluate search tasks for user intent, factual accuracy, and local relevance. Long-term remote work for people who have lived in an eligible location for at least five years.

10 hours per week China · Mexico Available in 6 countries China Mexico Norway South Korea United Kingdom United States

About This Project

We are currently looking for long-term participants for our new project, Lightspeed! If you are familiar with our Milky Way project, this is the next logical step to conquer the universe!

During this Search Engine Evaluation project, you will evaluate unique tasks, made by other users. To be successful, this project is accompanied by different tests and certifications to help you on your way.

The entries to evaluate will be of varied nature, from user intent to authentication of data accuracy.

Why This Work Matters

Thanks to this project, we will help develop and optimize current and future map and geo-localization applications, to produce more accurate and intuitive maps in terms of location, search functions and more.

Requirements

  • You have been living in one of the available locations for at least 5 years. Our evaluators must be familiar with the local businesses, points of interest, colloquialisms, etc.
  • You are a native or a fluent speaker of the language of the location where you are located and are a very fluent speaker of English.
  • You have access to a good internet connection and a computer.
  • You are available for at least 10 hours per week.
  • You are willing to take our certifications for this project.

Please note: This project requires a CV. To avoid application processing delays, please ensure yours is uploaded to your OneForma profile prior to applying.

Similar Projects

AI/ML Training Annotation

Multilingual AI Response And Rubric Evaluator

Evaluate multilingual AI reference responses and scoring rubrics, identify critical errors, and improve evaluation quality. Flexible remote work across seven selected language and location options.

Brazil · Indonesia Available in 7 countries Brazil Indonesia Malaysia Mexico Thailand United Kingdom Vietnam Flexible
Fixed rate per hour Apply
Languages Judging

Multilingual AI Response Evaluator And Prompt Writer

Evaluate AI responses, rewrite content so it sounds natural in your language, and create prompts that test model quality. Remote work for native French, Australian English, and Japanese specialists.

Australia · Canada Available in 5 countries Australia Canada France Japan United Arab Emirates Remote
Fixed rate per hour Apply
AI/ML Training Judging

Arabic AI Safety Evaluator

Review Arabic AI responses for harmful content, safety risks, and policy violations. Open to experienced native speakers in Switzerland, Saudi Arabia, or the UAE who have a personal MacBook.

Saudi Arabia · Switzerland Available in 3 countries Saudi Arabia Switzerland United Arab Emirates Remote
Fixed rate per hour Apply

Equal Opportunity At OneForma

OneForma welcomes experts from every background. Eligibility and selection are based on the requirements of each project, without discrimination based on race, ethnicity, gender, religion, disability, age, sexual orientation, cultural background, or any other characteristic protected by applicable law.

Choose your language or location

Select the option that matches your language and location.