Where you can live
Open to people living in United States.
Listed location: USA - Remote; San Francisco, CA; Ann Arbor, Michigan
Read from the posting text by our automatic check, which can be wrong. Confirm in the posting before you apply.
What the job is
Runs open-ended research on generative audio models, from neural audio codecs to steerable speech generation, and takes promising experiments toward production under real-time limits.
What they ask for
- Deep, demonstrated expertise in generative modeling such as diffusion, latent models, or controllable generation
- Strong mathematical grounding in statistical learning, including self-supervised and multimodal learning
- Designs controlled experiments and ablations that isolate what works
- Advanced proficiency in Python and PyTorch, including training models from scratch
- PhD or Master's in a related field, and/or equivalent industry experience
Nice to have
- Has shipped a model or system to production, ideally under real-time or streaming constraints
- Hands-on experience with neural audio codecs, TTS, STT, or speech-to-speech systems
- Has worked on interpretability or representation steering
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Deepgram