Cantonese Audio Evaluator

Join a high-impact audio AI research project as a Cantonese Audio Generalist Evaluator Expert. This role focuses on transcription, annotation, and evaluation tasks that are essential for training and benchmarking advanced language models. Ideal candidates will have strong academic or analytical backgrounds, be fluent in Cantonese and English, and possess a passion for translating complex audio and visual information into precise, well-structured text.

• Transcribe and Optimize Audio & Video
  • Listen to, analyze, and transcribe audio and video content in Cantonese, following detailed constraints and instructions.
  • Produce high-quality written outputs, with supporting work in English when required.
  • Ensure clarity, accuracy, and strict adherence to formatting and stylistic guidelines.
• Define and Document Evaluation Standards
  • Establish clear expectations for correct and high-quality responses in general consumer audio contexts.
  • Develop detailed evaluation rubrics and grading guidelines in Cantonese and English.
  • Document standards to ensure consistency across reviewers and model evaluations.
• Conduct Model Testing and Grading
  • Run prompts through language models and assess generated outputs.
  • Evaluate responses against predefined criteria for accuracy, completeness, and instructional clarity.
• Support Benchmarking and Quality Assurance
  • Participate in QA and review cycles to ensure tasks, rubrics, and outputs meet quality standards.
  • 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.
• Fluency in Cantonese and English (spoken and written).
• Available to commit 10–20 hours per week.

• College students or recent graduates.
• Background in linguistics, humanities, social sciences, or technical fields.
• Prior experience with transcription, annotation, evaluation, or research workflows.
• Interest in AI, language models, or applied research environments.

This is a short-term, structured engagement with a commitment of 10–20 hours per week.

Hourly rate of $50.

Fluency in Cantonese and English is required. Candidates must be able to work remotely.

Complete a short AI-led interview (approximately 15 minutes) as part of the application process. 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 while gaining hands-on exposure to real-world AI research and evaluation workflows.