Profile cover
V

AI Lyric-to-Melody Generation Researcher

Victoria Nakamura

Full-time · Job · Los_Angeles

About the role

Songwriter workflows are broken. The gap between 'I have these lyrics' and 'I have a melody that fits them' requires either expensive studio time with a session musician or months of music theory training. We're building the AI system that bridges that gap — generating musically coherent melodies from lyric text that a songwriter can iterate on, export to their DAW, and build into a finished track. The problem is fundamentally multimodal and underspecified. A lyric like 'the city lights reflect on rain-soaked streets' could map to a hundred different musical interpretations. We want to generate melodies that are surprising enough to inspire but grounded enough in the lyric's rhythm, syllable structure, and emotional valence to feel like they actually fit. The current research literature handles syllable-timed melody generation reasonably well; emotional mapping and stylistic coherence are where we need to push the frontier. You'll lead this research thread: designing architectures, running ablations, listening to hundreds of generated examples, and iterating toward something that songwriters actually want to use. You'll have access to a dataset of 400,000 licensed song pairs, GPU resources, and two collaborators — one from the music technology side and one from the language modeling side.

Responsibilities

  • Design and implement lyric-to-melody generation architectures
  • Develop emotional valence mapping between lyric content and musical mood
  • Build syllable-aware generation that preserves natural lyric rhythm
  • Run user studies with songwriters to evaluate musical inspiration quality
  • Publish research findings on controllable music generation
  • Iterate from research prototype to demo-quality system for product integration

Requirements

  • 6+ years in ML research with music AI, audio ML, or multimodal generation
  • Experience with symbolic music representation and MIDI-based generation models
  • Strong PyTorch skills with sequence-to-sequence architecture expertise
  • Understanding of music theory and compositional structure
  • Publication record or notable open-source work in music or audio ML

Benefits

  • Fully remote with flexible schedule
  • Top-of-market compensation
  • Research publication encouraged and supported
  • Access to licensed music dataset
  • Annual $5,000 equipment and conference budget

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch hugging face docker aws

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Drone Platform Integration & Network Support Engineer

RemoteAI company

Full-time

AI Resident UK/EMEA

RemoteAI company

Full-time

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

Senior Machine Learning Engineer (Clinical Team)

RemoteAI company

Full-time Senior

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$160k – $200k / year

AI Expertise

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch hugging face docker aws statistics

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile