Taiwanese Audio Generalist Evaluator Expert

Mercor is seeking a Taiwanese Audio Generalist Evaluator Expert to contribute to a high-impact audio AI research project with a leading research lab. In this role, you will work on transcription, annotation, and evaluation tasks that help train and benchmark advanced language models. This is a short-term, structured engagement ideal for candidates with strong academic or analytical backgrounds who are fluent in Traditional Chinese (Taiwan Mandarin) and English and enjoy translating complex audio and visual information into precise, well-structured text.

Listen to, analyse, and transcribe audio and video content in Traditional Chinese (Taiwan Mandarin), following detailed constraints and instructions.

Location Requirements

Taiwanese Audio Generalist Evaluator Expert

Traditional Chinese (Taiwan Mandarin) and English

Job Responsibilities

Transcribe and Optimise Audio & Video

Traditional Chinese (Taiwan Mandarin)

Define and Document Evaluation Standards

Traditional Chinese and English

Conduct Model Testing and Grading

Support Benchmarking and Quality Assurance

Minimum Qualifications

10–20 hours per week

Preferred Qualifications

Additional Role Details

Mercor is seeking a Taiwanese Audio Generalist Evaluator Expert to contribute to a high-impact audio AI research project with a leading research lab. In this role, you will work on transcription, annotation, and evaluation tasks that help train and benchmark advanced language models. This is a short-term, structured engagement ideal for candidates with strong academic or analytical backgrounds who are fluent in Traditional Chinese (Taiwan Mandarin) and English and enjoy translating complex audio and visual information into precise, well-structured text. Listen to, analyse, and transcribe audio and video content in Traditional Chinese (Taiwan Mandarin), following detailed constraints and instructions. Produce high-quality written outputs in Traditional Chinese, with supporting work in English when required. Ensure clarity, accuracy, and strict adherence to formatting and stylistic guidelines. Capture tone, intent, and region-specific expressions common in Taiwanese Mandarin usage. Establish clear expectations for correct and high-quality responses in general consumer audio contexts. Develop detailed evaluation rubrics and grading guidelines in Traditional Chinese and English. Document standards to ensure consistency across reviewers and model evaluations. Identify linguistic nuances, colloquialisms, and edge cases specific to Taiwanese Mandarin. Run prompts through language models and assess generated outputs. Evaluate responses against predefined criteria for accuracy, completeness, fluency, and instructional clarity. Provide structured feedback to improve model performance in Traditional Chinese audio tasks. Participate in QA and review cycles to ensure tasks, rubrics, and outputs meet Mercor’s quality bar. Maintain consistency and reliability before datasets are integrated into official benchmarks. Collaborate with project leads to resolve ambiguities and improve task design. Strong writing, editing, and critical thinking skills. Ability to work independently, manage time effectively, and meet deadlines. Native or near-native fluency in Traditional Chinese (Taiwan Mandarin, spoken and written) and professional fluency in English. Ability to accurately transcribe and analyse Taiwanese Mandarin audio content across general consumer contexts. Available to commit 10–20 hours per week. College students or recent graduates. Background in linguistics, humanities, social sciences, journalism, or technical disciplines. Prior experience with transcription, annotation, localisation, evaluation, or research workflows in Traditional Chinese. Familiarity with Taiwan-specific vocabulary, idiomatic expressions, and cultural context. Interest in AI, language models, or applied research environments. Complete a short AI-led interview (approximately 15 minutes). If selected, you will be onboarded and invited to begin project work. Work in a structured, goal-oriented project environment with clear tooling, guidelines, and support. Gain hands-on exposure to real-world AI research and evaluation workflows. Contribute directly to benchmarking and improving advanced multilingual language models. We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.

• Listen to, analyse, and transcribe audio and video content in Traditional Chinese (Taiwan Mandarin), following detailed constraints and instructions.
• Produce high-quality written outputs in Traditional Chinese, with supporting work in English when required.
• Ensure clarity, accuracy, and strict adherence to formatting and stylistic guidelines.
• Capture tone, intent, and region-specific expressions common in Taiwanese Mandarin usage.
• Establish clear expectations for correct and high-quality responses in general consumer audio contexts.
• Develop detailed evaluation rubrics and grading guidelines in Traditional Chinese and English.
• Document standards to ensure consistency across reviewers and model evaluations.
• Identify linguistic nuances, colloquialisms, and edge cases specific to Taiwanese Mandarin.
• Run prompts through language models and assess generated outputs.
• Evaluate responses against predefined criteria for accuracy, completeness, fluency, and instructional clarity.
• Provide structured feedback to improve model performance in Traditional Chinese audio tasks.
• Participate in QA and review cycles to ensure tasks, rubrics, and outputs meet Mercor’s quality bar.
• Maintain consistency and reliability before datasets are integrated into official benchmarks.
• Collaborate with project leads to resolve ambiguities and improve task design.
• Strong writing, editing, and critical thinking skills.
• Ability to work independently, manage time effectively, and meet deadlines.
• Native or near-native fluency in Traditional Chinese (Taiwan Mandarin, spoken and written) and professional fluency in English.
• Ability to accurately transcribe and analyse Taiwanese Mandarin audio content across general consumer contexts.
• Available to commit 10–20 hours per week.
• College students or recent graduates.
• Background in linguistics, humanities, social sciences, journalism, or technical disciplines.
• Prior experience with transcription, annotation, localisation, evaluation, or research workflows in Traditional Chinese.
• Familiarity with Taiwan-specific vocabulary, idiomatic expressions, and cultural context.
• Interest in AI, language models, or applied research environments.
• Complete a short AI-led interview (approximately 15 minutes).
• If selected, you will be onboarded and invited to begin project work.
• Work in a structured, goal-oriented project environment with clear tooling, guidelines, and support.
• Gain hands-on exposure to real-world AI research and evaluation workflows.
• Contribute directly to benchmarking and improving advanced multilingual language models.