This is a fully remote position, open to applicants in Germany.

📋 Description

• Identify realistic failures in search results where an AI model does not provide satisfactory responses.

• Develop and assess search queries.

• Record instances of failure.

• Draft guidelines and evaluation criteria for accurate responses.

• Analyze local relevance, source quality, outdated information, language discrepancies, incomplete answers, and region-specific inapplicability.

• Conduct multiple tests on queries before identifying failures.

⛳️ Requirements

• Research skills — proficiency in locating and validating information from various sources; adept at navigating diverse websites, databases, and documentation.

• Critical thinking — ability to detect inconsistencies among sources, identify outdated information, and recognize when something is irrelevant to a specific locale or context.

• Attention to detail — capable of noticing nuances in language, local variations (prices, regulations, requirements), and edge cases.

• Problem-solving mindset — comfortable with iteration and testing when solutions are not immediately apparent; remains resilient in the face of trial-and-error.

• Domain knowledge — preferably someone with experience in research, quality assurance, compliance, or similar fields that demand precision and source verification.

• Writing clarity — able to convey instructions and evaluation rubrics clearly, ensuring that others grasp the reasoning behind their logic.

• Locale knowledge — having a comprehensive understanding of their specific locale (local regulations, business practices, cultural nuances) is essential for identifying region-specific failures.

• Proficiency in the German language.