Seeking experienced music transcribers to create accurate multi-track MIDI transcriptions and symbolic music data for training and evaluating frontier generative AI music models. This part-time remote role requires expert skills in music transcription, notation, and production software.
Music Expert — AI Evaluation & Annotation (Generative Music)
Job description
Mercor is seeking professional musicians, music producers, and musicologists to evaluate and annotate AI-generated music for a frontier generative music AI laboratory.
In this role, you will complete structured evaluation tasks that transform subjective musical quality into high-quality data used to improve next-generation AI music models.
Your expertise will help AI systems better understand musical quality, production, composition, vocals, lyrics, and instruction-following across a wide range of genres and languages.
Key Responsibilities
Preference Labeling
Compare two AI-generated tracks created from the same prompt and determine which performs better across criteria such as:
- Faithfulness to the prompt
- Instruction following
- Audio fidelity
- Production quality
- Vocal quality
- Musicality
Provide clear, evidence-based written justifications for each evaluation.
Music Captioning
Create structured descriptions for music tracks, including:
- Genre and style
- Instrumentation
- Song structure with timestamps
- Key
- Tempo
- Musical feel
- Vocal characteristics
- Production style
- Musical era
Lyric Alignment
- Create karaoke-style word-by-word timestamps.
- Mark accurate start and end times for each lyric.
- Correct transcript errors such as:
- Missing words
- Repeated phrases
- Looping artifacts
- Pronunciation issues
Quality Evaluation
Apply standardized evaluation rubrics to ensure consistency and high-quality annotations across all assigned music tasks.
Ideal Qualifications
- Professional musician, producer, composer, musicologist, or equivalent music expert.
- Strong critical listening skills across multiple musical genres.
- Ability to evaluate music objectively using structured quality criteria.
- Comfortable writing clear, evidence-based explanations for musical judgments.
Bonus Qualifications
- Music production or audio mixing experience.
- Formal music theory training.
- Multilingual lyric proficiency.
- Experience working across multiple musical styles and genres.
Project Details
- Remote work
- Flexible hours
- Part-time engagement
- Short calibration process ("Rubric Academy") before project assignment
- Background check required
- Confidentiality agreement required
Projects will be matched to your strongest genres and language expertise.
Compensation
- $30–$65 per hour
Contract & Payment Terms
- Independent contractor engagement
- Fully remote work
- Flexible schedule
- Weekly payments through Stripe or Wise
- Projects may be extended, shortened, or concluded based on business needs and performance
Important Note
Mercor currently cannot support:
- H1-B candidates
- STEM OPT candidates
About Mercor
Mercor partners with leading AI labs and enterprises to train and improve frontier AI systems using human expertise.
Contributors help shape the future of generative music AI by evaluating, annotating, and improving AI-generated musical content across diverse genres and languages.
You will be redirected to the company's website to complete your application.