Research Staff, Voice AI Foundations [UK - Remote]

📋 Description

• Pioneer the development of Latent Space Models (LSMs) to solve fundamental data, scale, and cost
• Build next-generation neural audio codecs for extreme low bit-rate compression and high fidelity
• Develop steerable generative models that synthesize diverse human speech from codec latent
• Create embedding systems that factorize latent space into interpretable dimensions (speaker
• Leverage latent recombination to generate synthetic audio data at scale and train multimodal
• Design model architectures, training schemes, and inference algorithms for cost-efficient training

🎯 Requirements

• Strong mathematical foundation in statistical learning theory, self-supervised and multimodal
• Deep expertise in foundation model architectures and scaling training across modalities
• Proven ability to bridge theory and practice—derive novel formulations and implement them
• Demonstrated ability to build data pipelines for massive datasets
• Track record of designing controlled experiments to validate theoretical insights
• Experience optimizing models for real-world deployment, including hardware constraints and