Senior Research Engineer - Voice

Stack

Responsibilities

• ▹Develop and evaluate streaming and speech-to-speech systems for low-latency, interactive voice synthesis
• ▹Adapt models for new conditioning inputs (emotion, speed, prosody, speaker control, etc.)
• ▹Implement post-training optimization techniques (quantization, pruning, distillation) to improve efficiency and latency in real-time speech generation
• ▹Integrate and test novel architectures such as neural codecs, diffusion or flow-matching models to enhance realism and responsiveness
• ▹Contribute to defining new evaluation metrics for conversational speech, including latency-aware and online MOS prediction systems
• ▹Stay updated with the latest research in audio diffusion, autoregressive models, neural codecs and multimodal LLMs
• ▹Apply DPO (Direct Preference Optimization) and distillation to fine-tune large-scale speech models

Requirements

• ▹Strong understanding of generative modeling, ideally applied to sequential or multimodal data
• ▹Hands-on experience with large language models (LLMs) or similar transformer-based architectures
• ▹High proficiency in PyTorch, including distributed training and model optimization
• ▹Solid grasp of time-series modeling and tokenization, preferably for audio or speech
• ▹Demonstrated ability to prototype quickly, test hypotheses and iterate efficiently
• ▹Proven experience training deep learning models end-to-end, from data preparation to evaluation
• ▹Strong general software engineering skills to contribute to a large, shared research infrastructure

Nice to have

• ▹Experience with real-time or streaming architectures
• ▹Familiarity with state-of-the-art audio and speech generation architectures (diffusion models, neural codecs, flow-matching models, autoregressive decoders)
• ▹Experience with speech-to-speech or text-to-speech (TTS) systems
• ▹Original research contributions, such as publications or open-source work in top-tier venues (ICASSP, Interspeech, NeurIPS, ICML)

Soft skills