Senior Research Engineer - Audio Post-Training

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

Adapt models for new conditioning inputs (emotion, speed, prosody, speaker control, etc.) Develop and evaluate streaming and speech-to-speech systems for low-latency voice synthesis Implement post-training optimization techniques (quantization, pruning, distillation) Integrate and test novel architectures (neural codecs, diffusion, flow-matching models) Contribute to defining new evaluation metrics for conversational speech Stay updated with the latest research in audio diffusion, autoregressive models, neural codecs, and multimodal LLMs Apply DPO and distillation to fine-tune large-scale speech models