Uma candidatura completa num minuto
Currículo e carta de apresentação personalizados, prontos a enviar.
OpenKrill is launching an exciting language evaluation project and seeks Korean-speaking experts to join our team.
You will identify search-related failures where AI responses are inadequate, create test queries, document results, and write clear instructions and evaluation criteria.
Contract is freelance, remote ( Korea ), about 20 hours per week, starting ASAP, at $35/hour.
Are you passionate about languages, writing, and quality evaluation? We are launching an exciting language evaluation project and are looking for Korean-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.
local relevance, source quality, outdated information, language mismatches, incomplete answers, and region-specific inapplicability. Testing multiple queries before finding failures is expected.