ML Scientist, Next-Gen Speech Synthesis (Remote)

Rime Labs; United States; On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive base salary with early-stage equity

Visa sponsorship available

Access to proprietary recordings

Job summary

Rime Labs is looking for a Machine Learning Scientist to advance their voice AI technology. This role entails designing and evaluating speech synthesis models and collaborating on TTS frontend behavior with linguists.

The ideal candidate will have a PhD or equivalent expertise in speech, audio, or ML and a thorough understanding of contemporary speech synthesis literature. Rime offers competitive compensation, remote-friendly work, and opportunities for equity.

Qualifications

• Familiarity with speech synthesis literature like Tacotron and VITS.
• Hands-on training with neural codecs such as EnCodec and DAC.
• Experience with multi-modal modeling techniques.
• Attention to detail regarding data quality and annotation.
• Hands-on approach to data and training tasks.
• Knowledge of TTS frontend and collaboration with linguists.
• Strong skills in PyTorch for model training.

Responsibilities

• Design and train speech synthesis models.
• Drive research on multi-modal architectures.
• Collaborate on TTS frontend behavior and model choices.
• Build rigorous evaluation methodologies.

Skills

Speech synthesis expertise

Neural codecs training

Multi-modal modeling

Attention to data quality

PyTorch fundamentals

Education

PhD or equivalent research experience

Job description

Rime Labs is looking for a Machine Learning Scientist to advance their voice AI technology. This role entails designing and evaluating speech synthesis models and collaborating on TTS frontend behavior with linguists.

The ideal candidate will have a PhD or equivalent expertise in speech, audio, or ML and a thorough understanding of contemporary speech synthesis literature. Rime offers competitive compensation, remote-friendly work, and opportunities for equity.