Research Staff, Voice AI Foundations
Remote · San Francisco · Ann Arbor · Full-time · Remote · Posted Aug 23, 2026
At a glance
- Employment
- Full-time
- Workplace
- Remote
- Location
- Remote · San Francisco · Ann Arbor
About the role
- As a Member of the Research Staff, you will pioneer the development of Latent Space Models (LSMs) to solve fundamental data, scale, and cost challenges in building robust, contextualized voice AI.
- Your research will focus on advancing neural audio codecs, steerable generative models, embedding systems, and multimodal speech-to-speech architectures.
Responsibilities
- Build next-generation neural audio codecs that achieve extreme, low bit-rate compression and high fidelity reconstruction across a world-scale corpus of general audio.
- Pioneer steerable generative models that can synthesize the full diversity of human speech from the codec latent representation.
- Develop embedding systems that cleanly factorize the codec latent space into interpretable dimensions of speaker, content, style, environment, and channel effects.
- Leverage latent recombination to generate synthetic audio data at previously impossible scales, unlocking joint model and data scaling paradigms for audio.
- Endeavor to train multimodal speech-to-speech systems that can understand any human and produce empathic, human-like responses.
- Design model architectures, training schemes, and inference algorithms that are adapted for hardware at the bare metal.
Requirements
- Strong mathematical foundation in statistical learning theory, particularly in areas relevant to self-supervised and multimodal learning.
- Deep expertise in foundation model architectures, with an understanding of how to scale training across multiple modalities.
- Proven ability to bridge theory and practice to derive novel mathematical formulations and implement them efficiently.
- Demonstrated ability to build data pipelines that can process and curate massive datasets while maintaining quality and diversity.
- Track record of designing controlled experiments that isolate the impact of architectural innovations and validate theoretical insights.
- Experience optimizing models for real-world deployment, including knowledge of hardware constraints and efficiency techniques.
- History of open-source contributions or research publications that have advanced the state of the art in speech/language AI.
Workplace
- USA - Remote; San Francisco; Ann Arbor
Skills
- Speech-to-Text
- Text-to-Speech
- Latent Space Models
- Neural Audio Codecs
- Generative Models
- Embedding Systems
- Multimodal Speech-to-Speech Systems
- Statistical Learning Theory
- Multimodal Learning
- Foundation Model Architectures
- Data Pipelines
- Hardware Constraints
Show all 13 skills
- Inference Algorithms
