Research Engineer (Audio Synthesis) - Remote
San Francisco, California /
AI Foundation is adding to our Audio Synthesis research team. We are creating human voice models that are the most accurate, most easily trained, and with the least data necessary for near-lifelike results.
About The Role:
- You’d help create AI-first products - implement state-of-the-art research papers, and contribute towards company IP and technology stack, at scale.
- You’d work on cutting-edge deep learning, and audio synthesis problems with an emphasis on digital humans. An opportunity to collaborate with research scientists and engineers at the AI Foundation and its partnering institutions.
- You have experience (academic or industry) with Audio Synthesis, Deep Learning, and Signal Processing for human voice sysnthesis and numerical optimization.
- You have experience using Generative deep learning methods, esp. for audio synthesis.
- You have experience with Neural networks - CNNs, RNNs, Autoencoders, etc., and transfer learning.
- You can independently implement/evaluate ideas efficiently on a modern deep learning stack, such as Python, PyTorch, and GPU-enabled compute.
- You have implemented or published research papers from/at top academic conferences, such as InterSpeech, ICASSP, etc. on a modern deep learning stack for voice synthesis applications.
- You are a team player with a positive attitude, mindful, with good communication skills.
AI Foundation is a hybrid for-profit and non-profit advancing the science and application of AI-based generative technologies.
- We value work-life balance.
- We value your technical and personal skills growth.
- We have competitive salary and benefits.