Language Evaluation Expert (AI)

Location: Remote, UK

Rate: $38 per hour

Company

hirify.global is running an AI language evaluation project focused on validating search-related responses and regional accuracy.

What you will do

• Identify realistic search-related failures in AI-generated responses.
• Create and test search queries, iterating across multiple queries to find failures.
• Document issues involving local relevance, source quality, outdated information, language mismatches, and incomplete answers.
• Write clear instructions and evaluation criteria for correct answers.
• Assess region-specific applicability, including local regulations, prices, requirements, and cultural nuances.

Requirements

• Strong research skills and the ability to verify information across multiple sources, websites, databases, and documentation.
• Critical thinking skills for identifying contradictions, outdated information, and context-specific inaccuracies.
• High attention to detail and a problem-solving mindset.
• Clear writing skills for explaining reasoning, instructions, and evaluation rubrics.
• Deep familiarity with a specific locale, including local regulations, business practices, and cultural nuances.
• Background in research, quality assurance, compliance, or another precision-focused field is preferred.

Culture & Benefits

• Remote freelance work for an ongoing project.
• Part-time commitment of 20 hours per week.
• Project start: ASAP.