The work

You will test how well conversational AI uses personal context. You will create multi-turn prompts, review responses, compare outputs, and explain your judgments in clear written feedback.

• Create and run conversational prompts that usually span one to five turns and are grounded in personal experiences.
• Check whether responses follow the prompt, use relevant information correctly, and apply personalization naturally.
• Identify unsupported claims, incorrect inferences, hallucinations, forced connections, and unnecessary explanations.
• Compare responses side by side for helpfulness, usability, naturalness, accuracy, and overall quality.
• Write concise, evidence-based rationales that refer to specific conversation turns and give constructive feedback.
• Review debugging information to confirm that summaries and relevant data sources were used correctly.
• Delete the evaluation conversations from your own Gemini history after review.

What it pays and takes

This is a remote, part-time contract role open worldwide. The work requires at least 20 hours per week and strong Spanish reading and writing ability.

• Pay: $15 per hour.
• Time: 20+ hours per week.
• Location: Remote and open worldwide.
• Language: Strong Spanish reading and writing ability.
• Experience level: Intermediate.
• You should be able to analyze nuanced or unclear AI responses and recognize incorrect personalization, poor inferences, and forced connections.
• You need clear, structured written communication, close attention to detail, and the ability to work independently.
• You need a reliable computer and internet connection.
• You must use your own primary personal Google account and turn on the data sources this work uses. The job page on the hiring site says these are your past Gemini conversations, Gmail, Google Search and YouTube activity.
• The job page on the hiring site does not say how far back this activity goes, how long the data is kept, what causes its deletion, who receives the data, or how to withdraw or revoke Google access after work starts.
• A bachelor's degree or equivalent experience in policy, law, ethics, linguistics, journalism, computer science, or a related analytical field is helpful but not required.
• Experience in data annotation, AI quality evaluation, content moderation, or related work is valuable.

How it works

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

About AI training work

AI training is the human work behind artificial intelligence. People create examples, review model responses, and give feedback so AI systems become more accurate, useful, and natural. OpenTrain helps people find these roles, build a profile, and apply to projects in one place.