About OpenTrain
OpenTrain is the centralized, open platform where AI training and data-labeling freelancers find work, consolidate opportunities across platforms, and build a unified AI training portfolio they control. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career.
About this role
OpenTrain is recruiting a Polish AI Personalization Quality Evaluator to assess how effectively Gemini uses personal context to make responses more relevant and helpful. You will create realistic multi-turn prompts based on personal experiences, evaluate personalized responses, compare model outputs, and provide structured feedback for an AI training project.
What you will do
- Design and execute multi-turn conversational prompts that test the use of personal information and experiences.
- Evaluate whether model responses appropriately use the available context.
- Check responses for grounding, unsupported inferences, hallucinations, and forced connections.
- Assess whether personal information is integrated naturally without awkward over-explanation.
- Compare and rank two model responses for helpfulness, ease of use, enjoyment, and overall quality.
- Write clear rationales that reference specific conversation turns and provide detailed annotations.
- Verify debugging information and data-source use, then delete evaluation conversations to maintain clean chat history.
Required skills
- Professional ability to read and write in Polish.
- Strong analytical judgment when evaluating nuanced or ambiguous AI responses.
- Ability to design creative multi-turn prompts based on personal context.
- Clear, structured written communication and attention to detail.
- Ability to recognize incorrect personalization, unsupported inferences, hallucinations, and subtle differences in response naturalness.
- A bachelor's degree or equivalent experience in policy, law, ethics, linguistics, journalism, computer science, or a related analytical field is helpful.
- Experience in data annotation, AI quality evaluation, content moderation, or a related role is preferred.
- Reliable computer equipment and internet access, and willingness to use a primary personal Google account and relevant personal data sources for evaluation.
Schedule, location, and pay
This is a remote contractor role with an engagement length of one month. Availability of at least 4 hours per day and up to 40 hours per week is required, including 4 hours of overlap with PST. The rate is $20 per hour. The role is focused on Polish-language evaluation and is open to remote contractors where permitted.
Why work with OpenTrain
OpenTrain gives freelancers one place to manage AI training opportunities instead of rebuilding proof of work on every platform. A stronger OpenTrain profile helps you show credible experience, discover roles that match your skills, and turn AI training and data-labeling work into a long-term portfolio.