🛠 Tech Stack

💼 About This Role

You'll join a visionary team to develop text-to-speech and voice cloning models for interactive avatars. You'll push the limits of synthetic voice generation, building efficient training pipelines and custom validation metrics. This role offers a chance to redefine generative content in gaming, entertainment, and education.

🎯 What You'll Do

• Design and optimize text-to-speech models for voice actor authenticity.
• Experiment with neural TTS and voice cloning architectures.
• Define validation strategies and implement custom evaluation metrics.
• Contribute to MLOps practices and production infrastructure.

📋 Requirements

• Experience with deep learning frameworks (PyTorch, TensorFlow, or JAX).
• Understanding of audio processing (sampling, spectrograms, vocoders).
• Experience training text-to-speech and voice cloning models.
• Familiarity with speech synthesis models (WaveNet, Tacotron, VITS).

✨ Nice to Have

• Experience with voice cloning models like XTTS, YourTTS.
• Experience with transformers and diffusion models.
• Ability to implement ideas from research papers.

🎁 Benefits & Perks

• 🚀 Cutting-edge AI work on novel interactive platform.
• 💻 Hybrid work flexibility.
• 🌍 Global team with diverse innovators.
• 📈 Opportunity to shape foundational technology.