Professional Skills

• Advanced knowledge in relevant areas of mathematics and statistics.
• Working knowledge of techniques for designing deep nets, hyperparameter optimization, visualization, and interpretation.
• Experience with deep learning projects, including both failures and successes.
• Good understanding of deep generative models (autoregressive models, GANs, VAEs, diffusion models, flow-based models, or combinations).

Preferred Qualifications

• Degree in computer science or a related field.
• Knowledge of Digital Signal Processing theory.
• Knowledge of speech processing and TTS (Text-to-Speech).
• Participation in DS/ML/DL competitions (e.g., Kaggle).
• Knowledge of CUDA and interest in developing custom CUDA kernels.
• Experience deploying machine learning models.

Benefits

• Engage in real research with deep generative models of audio in a small, scientifically-minded team.
• Freedom to explore and implement your own ideas.
• Potential publication opportunities.