Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
OpenKrill is seeking Indonesian-speaking evaluators to join an ongoing language evaluation project. You will test AI responses, craft targeted search queries, and document failures with clear instructions and criteria.
The freelance role requires about 20 hours per week, remote from Indonesia, with a rate of $25 per hour. Start date is ASAP and work will focus on locale-specific accuracy and up-to-date information.
Are you passionate about languages, writing, and quality evaluation? We are launching an exciting language evaluation project and are looking for Indonesian-speaking experts to join our team.
Identify realistic search-related failures where an AI model provides inadequate responses. Create search queries, test them, document what went wrong, and write instructions and evaluation criteria for correct answers.
Common issues: local relevance, source quality, outdated information, language mismatches, incomplete answers, and region-specific inapplicability. Testing multiple queries before finding failures is expected.