Rime
Machine Learning Scientist
United States · Remote · Full-time · Posted May 15, 2026
- Experience
- No specific number of years stated; PhD or equivalent research experience, or a track record that makes the credential irrelevant.
- Education
- PhD or equivalent research experience in speech, audio, ML, or computational linguistics, or a track record that makes the credential irrelevant.
- Visa sponsorship
- Visa sponsorship available
About the job
Designs and evaluates speech synthesis and speech-understanding models, with a focus on duplex multimodal systems, speech representations, and quality evaluation.
What you'll do
- Design, train, and evaluate autoregressive and non-autoregressive speech synthesis models.
- Research full- and half-duplex multimodal architectures, including unified S2S systems, and iterate on speech representations.
- Develop objective and perceptual evaluation and collaborate with linguists on TTS frontend behavior.
What they ask for
- Deep familiarity with contemporary and historical speech synthesis research.
- Hands-on training with neural codecs and experience with multiple speech representation choices.
- Experience with full- or half-duplex multimodal modeling.
- Strong PyTorch fundamentals, including training loops, distributed training, and model internals.
Nice to have
- Multilingual TTS experience or a background in prosody or paralinguistics.
- Published work in speech, audio, or core ML venues; experience taking research models to production.
Tools
PyTorch, Tacotron, FastSpeech, VITS, VALL-E, EnCodec, DAC, Mimi
AI focus
Research and development of speech synthesis and speech understanding, including full- and half-duplex multimodal systems and TTS.
Model-written summary · the original posting is authoritative