Research and develop state-of-the-art voice synthesis models including TTS and voice cloning. Collaborate with cross-functional teams to integrate these models into production-ready pipelines for expressive and natural-sounding speech.
BRAHMA
2 Remote Job Openings at BRAHMA
The role involves researching and building deep learning systems for expressive speech generation and developing state-of-the-art generative systems for video and audio synthesis. As a senior member, the engineer will shape core infrastructure, set best practices, and mentor junior staff while delivering high-quality ML pipelines in production.
