Remote Bilingual LLM Evaluator (Urdu-English)

Mercor; United States; Remote; USD 20,664 - 27,552; Part time

Job summary

Mercor is seeking a Generalist proficient in English and Urdu to conduct evaluations for AI models from a remote location. The successful candidate will engage in high-quality data generation, fact-checking, and assessment of AI responses. A Bachelor's degree and fluency in Urdu are essential.

This position demands attention to detail and significant experience with large language models. The compensation ranges from $15 to $20 per hour.

Qualifications

• Native speaker in Urdu with excellent writing skills in English.
• Significant experience using large language models (LLMs).
• Strong attention to detail and background in analytical thinking.

Responsibilities

• Conduct fact-checking using trusted public sources and external tools.
• Generate high-quality human evaluation data and assess responses.
• Ensure model responses align with expected behavior and guidelines.

Skills

Native speaker in Urdu

Excellent writing skills in English

Strong attention to detail

Significant experience using large language models (LLMs)

Background in structured analytical thinking

Education

Bachelor's degree

Job description

Mercor is seeking a Generalist proficient in English and Urdu to conduct evaluations for AI models from a remote location. The successful candidate will engage in high-quality data generation, fact-checking, and assessment of AI responses. A Bachelor's degree and fluency in Urdu are essential.

This position demands attention to detail and significant experience with large language models. The compensation ranges from $15 to $20 per hour.