Gen AI Audio Researcher

As a Gen AI Researcher for Audio at Brahma, your role will involve researching and developing state-of-the-art voice synthesis models, building and fine-tuning models using frameworks like PyTorch and HuggingFace, designing training pipelines and datasets for scalable voice model training, exploring techniques for emotional expressiveness, multilingual synthesis, and speaker adaptation, working closely with product and creative teams to ensure models meet quality and production constraints, and staying updated on academic and industrial trends in speech synthesis and related fields. Key Responsibilities: - Research and develop state-of-the-art voice synthesis models such as TTS, voice cloning, and speech-to-speech. - Build and fine-tune models using frameworks like PyTorch and HuggingFace. - Design training pipelines and datasets for scalable voice model training. - Explore techniques for emotional expressiveness, multilingual synthesis, and speaker adaptation. - Collaborate with cross-functional teams to integrate your work into production-ready pipelines. - Stay on top of academic and industrial trends in speech synthesis and related fields. Qualifications Required: - Strong background in machine learning and deep learning, with a focus on speech/audio. - Hands-on experience with TTS, voice cloning, or related voice synthesis tasks. - Proficiency with Python and PyTorch; experience with libraries like torchaudio, ESPnet, or similar. - Experience training models at scale and working with large audio datasets. - Familiarity with vocoders and transformer-based architectures. - Strong problem-solving skills and the ability to work autonomously in a remote-first environment. Brahma is a pioneering enterprise AI company that develops Astras, AI-native products designed to help enterprises and creators innovate at scale. Part of the DNEG Group, Brahma brings together Hollywood's leading creative technologists, innovators in AI and Generative AI, and thought leaders in the ethical creation of AI content.,