Deep Learning Scientist - Speech Synthesis

We are seeking a Deep Learning Scientist - Speech Synthesis to support the development of next-generation speech AI technologies. This role focuses on advancing text-to-speech (TTS) systems through deep learning, model optimization, and speech data engineering. The selected candidate will contribute to innovative speech applications used at large scale while collaborating with cross-functional engineering and research teams., * Train speech synthesis models, including mel spectrogram and vocoder models.

• Measure, benchmark, and optimize model performance across multiple use cases.
• Maintain and improve text-to-speech evaluation systems.
• Analyze model accuracy, quality, and bias, recommending improvements where needed.
• Develop processes for speech data preparation, augmentation, filtering, and dataset creation.
• Characterize speech model performance and quality metrics across platforms.
• Collaborate with cross-functional teams to develop and deliver new product features.
• Participate in software development, design reviews, testing, and code reviews.
• Troubleshoot technical issues and contribute to continuous product improvements.

• Master''s degree or Ph.D. in Computer Science, Electrical Engineering, Artificial Intelligence, Applied Mathematics, Linguistics, Computational Linguistics, or a related field (or equivalent experience).
• Minimum 5 years of relevant industry experience.
• Strong Python programming skills.
• Solid understanding of software development principles and programming fundamentals.
• Strong knowledge of machine learning and deep learning techniques, including CNNs, RNNs, LSTMs, and Transformers.
• Experience applying deep learning to speech synthesis, large language models, or speech-to-speech translation.
• Hands-on experience with speech synthesis technologies and voice cloning.
• Experience training speech models.
• Strong proficiency with PyTorch.
• Knowledge of speech signal processing concepts, including FFT, MFCC, and mel spectrograms.
• Experience using version control systems such as Git, Gerrit, or GitLab.
• Excellent communication and collaboration skills., * Fluency in one or more languages such as Spanish, Mandarin, German, Japanese, Russian, French, Arabic, Hindi, Korean, Italian, or Portuguese.
• Experience with multilingual or code-switched text-to-speech systems.
• Experience with voice cloning and cross-lingual voice cloning.
• Knowledge of text normalization (TN) and inverse text normalization (ITN) using neural networks or WFST.
• Experience with grapheme-to-phoneme (G2P) systems for multiple languages.
• Interest in linguistics, phonetics, and speech technologies.
• Strong C++ programming skills.
• Familiarity with GPU technologies such as CUDA, cuDNN, or TensorRT.
• Experience deploying machine learning models to cloud, data center, or embedded environments., * Candidates should be comfortable working in a collaborative, fast-paced environment while contributing to cutting-edge speech AI technologies.