About this role
Research Scientist for Speech Synthesis at Oddin. Location: Netherlands. Role: design TTS, train models, deploy pipelines Requirements: Develop text-to-speech and voice cloning models; build training/deployment pipelines; validate and measure quality; work with large text and speech datasets; implement MLOps. Category: Research and Development (R&D) Seniority: Mid Level Tools: PyTorch, TensorFlow, JAX, WaveNet, Tacotron, VITS, XTTS, YourTTS, diffusion models, Python Commitment: Full Time, Part Time, Contract, Internship, Temporary, Seasonal, Volunteer Workplace: Hybrid Languages: English