Speech & Audio ML Research Scientist — Next‑Gen Architect

Institute of Foundation Models; Paris; Presencial; EUR 90 000 - 150 000; Tempo integral

Resumo da oferta

The Institute Of Foundation Models in Paris is seeking a Research Scientist specializing in speech/audio machine learning to contribute to the design and training of state-of-the-art end-to-end neural speech models.

You will focus on developing core IP, moving beyond cascaded ASR→TTS toward native audio-to-audio multimodal architectures, collaborating with researchers, data scientists and engineers.

Qualificações

• PhD or MSc in Computer Science with a focus on Deep Learning, Signal Processing, or Computational Linguistics.
• Record of Research: Published work in top-tier venues (NeurIPS, ICLR, ICASSP, Interspeech).

Responsabilidades

• Architectural Design: Develop novel neural architectures for low-latency speech-to-speech translation and generation (e.g., Diffusion, Flow-matching, Transformer-based audio LLMs).
• Loss Function Engineering: Design and implement custom objective functions to optimize prosody (emotions, intelligibility, naturalness).
• Experimental Iteration: Conduct large-scale training runs, performing ablation studies on model architecture and tokenization strategies.
• Evaluation Frameworks: Establish rigorous internal benchmarks using both objective metrics (WER, MCD) and subjective human-in-the-loop (MOS) testing.

Conhecimentos

Speech/audio ML

Research publication track record

Formação académica

PhD or MSc in Computer Science (Deep Learning / Signal Processing / Computational Linguistics)

Descrição da oferta de emprego

The Institute Of Foundation Models in Paris is seeking a Research Scientist specializing in speech/audio machine learning to contribute to the design and training of state-of-the-art end-to-end neural speech models.

You will focus on developing core IP, moving beyond cascaded ASR→TTS toward native audio-to-audio multimodal architectures, collaborating with researchers, data scientists and engineers.