Description
We are looking for an intern to explore speech synthesis, audio generation and reasoning techniques. The ideal candidate will be very familiar with audio generation, speech synthesis and large language models.
Responsibilities
- Develop audio generation and speech synthesis methods
- Explore methods for LLM reasoning
- Build automated evaluation pipelines to assess quality of the synthetic data
- Optimize developed models for efficient inference
Minimum Qualifications
- Bachelor’s degree in Computer Science or equivalent
- Demonstrable experience in training deep learning system on multiple GPUs in Pytorch
- Demonstrable experience in audio, text to speech, speech to text technologies
Preferred Qualifications
- Studying for Masters Degree or PhD in Computer Science, Machine Learning or equivalent
- Demonstrable experience with diffusion and/or autoregressive audio generation models
- Publications in audio generation at well known conferences
