Research Staff, Voice AI Foundations - Remote
Salary not listed • Remote • The Netherlands • Full-time
Posted 20d ago
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Research Engineer
About the job
Deepgram is seeking a Research Staff member to pioneer the development of Latent Space Models (LSMs), a novel approach to address fundamental data, scale, and cost challenges in building robust, contextualized voice AI. This role involves pushing the boundaries of audio AI by developing next-generation neural audio codecs, steerable generative models, and advanced embedding systems. The goal is to create entirely new paradigms for audio AI that make voice interaction accessible to everyone, overcoming limitations of current sequence modeling. You will focus on solving complex problems related to data scarcity, high dimensionality, and computational costs in audio processing.
Responsibilities
- Develop next-generation neural audio codecs for extreme low bit-rate compression and high fidelity reconstruction.
- Pioneer steerable generative models for synthesizing diverse human speech from latent representations.
- Develop embedding systems to factorize codec latent space into interpretable dimensions for precise control.
- Leverage latent recombination to generate synthetic audio data at unprecedented scales.
- Train multimodal speech-to-speech systems for understanding and producing human-like responses.
- Design model architectures, training schemes, and inference algorithms optimized for cost-efficient training and real-time inference.
Requirements
- Strong mathematical foundation in statistical learning theory, especially self-supervised and multimodal learning.
- Deep expertise in foundation model architectures and scaling training across modalities.
- Proven ability to bridge theory and practice, deriving novel mathematical formulations and implementing them efficiently.
- Demonstrated ability to build data pipelines for processing and curating massive, diverse datasets.
- Track record of designing controlled experiments to validate theoretical insights and architectural innovations.
- Experience optimizing models for real-world deployment, considering hardware constraints and efficiency.