Profile cover
E

AI Prosody Transfer Fine-tuning Engineer

Elena Cohen

Full-time · Job · New_York

About the role

Prosody is the rhythm, stress, and intonation of spoken language — the difference between a synthetic voice that sounds robotic and one that sounds natural is almost entirely in the prosody. A voice synthesis model that gets the words right but the timing, emphasis, and pitch contours wrong produces speech that listeners find difficult to trust or engage with, even when they can't articulate exactly why it sounds off. Prosody transfer — taking the expressive characteristics of a source speaker and applying them to a target voice — is the mechanism by which we give synthesized voices stylistic personality. We build voice synthesis infrastructure for 70 media and communications clients. Our base synthesis models are strong. The frontier capability we're building is fine-grained prosody control: fine-tuning models to transfer speaking style from reference audio to target voices with minimal artifacts. You'll work on the prosody transfer training pipeline: curating reference audio datasets, designing fine-tuning objectives that separate prosodic style from speaker identity, and running ablations that measure how much of a source speaker's expressiveness is preserved in the transfer. The output is voice synthesis that sounds like it has a personality, not just pronunciation.

Responsibilities

  • Design fine-tuning objectives separating prosodic style transfer from speaker identity components
  • Curate and annotate reference audio datasets capturing prosodic style dimensions across speaking contexts
  • Run systematic ablations measuring how fine-tuning parameters affect style transfer versus identity leakage
  • Build prosody evaluation metrics correlating with human naturalness ratings
  • Implement prosody conditioning controls enabling clients to specify expressiveness level at inference time
  • Monitor prosody transfer quality across accents, speaking rates, and emotional register variations

Requirements

  • 3+ years in speech ML or voice synthesis with prosody, TTS, or voice conversion experience
  • Strong Python and PyTorch skills with sequence-to-sequence or audio generation model fine-tuning
  • Understanding of prosodic features: pitch, duration, energy, and their perceptual effects
  • Experience with audio dataset curation, annotation, and quality control
  • Familiarity with speaker disentanglement or voice conversion model architectures

Benefits

  • Fully remote with flexible schedule
  • Health and dental insurance
  • $2,500 annual professional development budget
  • 401(k) with match
  • Equity options

Keep exploring related roles

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

Categories

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python pytorch hugging face statistics sql

Related remote AI jobs

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

Browse all jobs

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

RemoteAI company

Full-time Senior

Technical Writer

RemoteAI company

Part-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

Conversational Modelling Research Engineer

RemoteAI company

Full-time

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$80k – $100k / year

AI Expertise

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python pytorch hugging face statistics sql pandas

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