Profile cover
D

AI Voice Cloning Researcher

Daniel Sokolov

Full-time · Job · Los_Angeles

About the role

Our text-to-speech platform creates custom voice models from as little as 30 minutes of recorded audio. Media companies use our voices for audiobook narration, podcast production, and content localization across 12 languages. The quality bar is extreme — listeners need to believe these are real human voices. You'll push the frontier of few-shot voice cloning: improving speaker similarity from limited reference audio, reducing artifacts in emotional speech synthesis, and building the evaluation framework that measures voice quality beyond standard MOS scores. The current system produces good voices. We need someone who can make them indistinguishable. This is a research-heavy role with production constraints. Every improvement needs to run at inference speeds fast enough for real-time streaming. You'll balance acoustic quality against latency, and publishable research against shipping deadlines. We encourage conference submissions, but production readiness comes first.

Responsibilities

  • Advance few-shot voice cloning quality from limited reference audio
  • Reduce synthesis artifacts in emotional and expressive speech
  • Build evaluation frameworks beyond MOS for voice quality measurement
  • Optimize voice models for real-time streaming inference
  • Publish research findings at speech and audio conferences

Requirements

  • 5+ years in speech synthesis or audio ML research
  • Strong PyTorch skills for generative audio models
  • Published work in TTS, voice conversion, or speech processing
  • Experience with vocoder architectures and audio signal processing
  • Ability to balance research quality with production shipping requirements

Benefits

  • Fully remote — US time zones
  • Senior equity package
  • Dedicated research GPU allocation
  • Conference travel and publication support

Keep exploring related roles

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

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$160k – $200k / year

AI Expertise

AI & Machine Learning Engineers

Skills

python pytorch tensorflow 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

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

Apply — create free profile