NZ English Audio Evaluator Expert at Mercor

NZ English Audio Evaluator Expert | $50/hr | Worldwide Remote

Mercor is seeking a skilled English (New Zealand) Audio Generalist Evaluator Expert to support a high-impact AI audio research project with a leading research lab. This short-term, structured engagement involves transcription, annotation, and evaluation tasks that help train and benchmark advanced language models. Ideal for candidates with strong analytical backgrounds who are fluent in New Zealand English and enjoy translating complex audio and visual content into precise, well-structured text.

Key Responsibilities

• Transcribe & Optimise Audio/Video: Listen to, analyse, and transcribe audio and video content in New Zealand English, capturing nuances such as tone, register, regional expressions, Māori loanwords, and contemporary NZ English usage.
• Define Evaluation Standards: Establish clear expectations for high-quality responses in general consumer audio contexts, develop detailed rubrics and grading guidelines, and document standards to ensure consistency across reviewers.
• Conduct Model Testing & Grading: Run prompts through language models, evaluate outputs against criteria for accuracy, fluency, and completeness, and provide structured feedback to improve model performance.
• Support Benchmarking & QA: Participate in quality assurance cycles, maintain consistency across datasets, and collaborate with project leads to resolve ambiguities and refine task design.

Minimum Qualifications

• Native or near-native fluency in New Zealand English (spoken and written)
• Strong familiarity with NZ regional vocabulary, accents, and Māori linguistic influences
• Excellent writing, editing, and critical thinking skills
• Ability to work independently and meet deadlines
• Available to commit 10–20 hours per week

Preferred Qualifications

• College students or recent graduates welcome
• Background in linguistics, humanities, journalism, translation/localisation, or social sciences
• Prior experience with transcription, annotation, or AI evaluation workflows
• Familiarity with differences between NZ English, Australian English, and other major varieties
• Interest in AI, language models, or applied research environments

Application Process

Complete a short AI-led interview (approximately 15 minutes). Selected candidates will be onboarded and invited to begin project work promptly.