Research Staff, Voice AI Foundations [UK - Remote]

Voice is the most natural modality for human interaction with machines. However, current sequence modeling paradigms based on jointly scaling model and data cannot deliver voice AI capable of universal human interaction. The challenges are rooted in fundamental data problems posed by audio: real-world audio data is scarce and enormously diverse, spanning a vast space of voices, speaking styles, and acoustic conditions. Even if billions of hours of audio were accessible, its inherent high dimensionality creates computational and storage costs that make training and deployment prohibitively expensive at world scale. We believe that entirely new paradigms for audio AI are needed to overcome these challenges and make voice interaction accessible to everyone.

The Role As a Member of the Research Staff, you will pioneer the development of Latent Space Models (LSMs), a new approach that aims to solve the fundamental data, scale, and cost challenges associated with building robust, contextualized voice AI. Your research will focus on solving one or more of the following problems:

• 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, from casual conversation to highly emotional expression to complex multi-speaker scenarios with environmental noise and overlapping speech.

• Develop embedding systems that cleanly factorize the codec latent space into interpretable dimensions of speaker, content, style, environment, and channel effects -- enabling precise control over each aspect and the ability to massively amplify an existing seed dataset through "latent recombination".

• 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 1) understand any human irrespective of their demographics, state, or environment and 2) produce empathic, human-like responses that achieve conversational or task-oriented objectives.

• Design model architectures, training schemes, and inference algorithms that are adapted for hardware at the bare metal enabling cost efficient training on billion-hour datasets and powering real-time inference for hundreds of millions of concurrent conversations.

We are seeking researchers who:

• See "unsolved" problems as opportunities to pioneer entirely new approaches

• Can identify the one critical experiment that will validate or kill an idea in days, not months

• Have the vision to scale successful proofs-of-concept 100x

• Are obsessed with using AI to automate and amplify your own impact

If you find yourself energized rather than daunted by these expectations - if you're already thinking about five ideas to try while reading this - you might be the researcher we need. This role demands obsession with the problems, creativity in approach, and relentless drive toward elegant, scalable solutions. The technical challenges are immense, but the potential impact is transformative.

It's Important to Us That You Have

• 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 - someone who can both 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

Ideal Researcher Profile An ideal researcher, as evidenced by the recurring themes across these foundational papers, excels in five key areas: (1) Statistical & Mathematical Foundations, (2) Algorithmic Innovation & Implementation, (3) Data-Driven & Scalable Systems, (4) Hardware & Systems Understanding, and (5) Rigorous Experimental Design. Below is a synthesis of how each paper highlights these qualities, with references illustrating why they matter for building robust, impactful deep learning models.

1. Statistical & Mathematical Foundations

Across all papers - particularly in the problem statements of Whisper or Rectified Flow Transformers - the authors present assumptions (e.g., "scaling data leads to zero-shot robustness" or "straight-line noise injection improves sample efficiency") and systematically verify them with thorough empirical results. An ideal researcher similarly grounds new ideas in well-formed, testable hypotheses.

1. Algorithmic Innovation & Implementation

Many references (Whisper, neural discrete representation learning, Mamba-2) highlight releasing code or pretrained models, enabling the broader community to replicate and build upon new methods. This premise of collaboration fosters faster progress.

1. Data-Driven & Scalable Systems

A recurring strategy is to vary sources of data or the order of tasks. Whisper trains on multilingual tasks, BASE TTS uses subsets/stages for pretraining on speech tokens, and phi-3 deploys multiple training phases (web data, then synthetic data). This systematic approach to data underscores how an ideal researcher designs training curricula and data filtering protocols for maximum performance.

1. Hardware & Systems Understanding

Papers like Mamba-2 in Transformers are SSMs and the In-Datacenter TPU work show how exploiting specialized matrix decomposition, custom memory hierarchies, or quantization approaches can lead to breakthroughs in speed or energy efficiency.

1. Rigorous Experimental Design

Whisper's out-of-distribution speech benchmarks, SoundStream's evaluation on speech + music, or Mamba-2's performance on multi-query associative recall demonstrate the importance of specialized challenge sets. Researchers who craft or adopt rigorous benchmarks and "red-team" their models (as in phi-3 safety alignment) are better prepared to address real-world complexities.

Summary Overall, an ideal researcher in deep learning consistently demonstrates:

• A solid grounding in theoretical and statistical principles

• A talent for proposing and validating new algorithmic solutions

• The capacity to orchestrate data pipelines that scale and reflect real-world diversity

• Awareness of hardware constraints and system-level trade-offs for efficiency

• Thorough and transparent experimental practices

These qualities surface across research on speech (Whisper, BASE TTS), language modeling (Scaling Laws, phi-3), specialized hardware (TPU, Transformers are SSMs), and new representation methods (VQ-VAE, FSQ, SoundStream). By balancing these attributes - rigorous math, innovative algorithms, large-scale data engineering, hardware-savvy optimizations, and reproducible experimentation - researchers can produce impactful, trustworthy advancements in foundational deep learning.

Foundational Papers This job description was generated through analysis of the following papers:

• Robust Speech Recognition via Large-Scale Weak Supervision (arXiv:2212.04356)

• Moshi: a speech-text foundation model for real-time dialogue (arXiv:2410.00037)

• Scaling Rectified Flow Transformers for High-Resolution Image Synthesis (arXiv:2403.03206)

• Scaling Laws for Neural Language Models (arXiv:2001.08361)

• BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data (arXiv:2402.08093)

• In-Datacenter Performance Analysis of a Tensor Processing Unit (arXiv:1704.04760)

• Neural Discrete Representation Learning (arXiv:1711.00937)

• SoundStream: An End-to-End Neural Audio Codec (arXiv:2107.03312)

• Finite Scalar Quantization: VQ-VAE Made Simple (arXiv:2309.15505)

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone (arXiv:2404.14219)

• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality (arXiv:2405.21060)