Senior Audio AI Engineer – TTS / Speech Synthesis - Remote

Overview

As a Senior Audio AI Engineer at Awarri, you will play a pivotal role in advancing the naturalness and quality of our Text-to-Speech (TTS) systems, focused on African languages and accents, contributing to inclusive AI technologies.

In Short

• Work on impactful projects shaping the future of AI in Africa.
• Collaborate with a globally distributed team of engineers and linguists.
• Optimize neural TTS models for prosody and expressiveness.
• Evaluate and fine-tune neural vocoders for audio quality.
• Lead evaluations of TTS quality and collaborate with linguistic teams.
• Prepare TTS systems for product integration and deployment.
• Develop APIs and backend services for TTS deployment.
• Proficiency in Python and TypeScript for model development.
• 3+ years of experience in TTS or speech generation systems.
• Experience with audio processing tools and scalable AI applications.

Requirements

• Deep knowledge of neural TTS architectures.
• Experience with machine learning frameworks like TensorFlow or PyTorch.
• Familiarity with FastAPI, Flask, and cloud environments.
• Experience working with multilingual or low-resource speech data.
• Comfort working remotely and asynchronously.
• Ability to debug complex model behavior.

Benefits

• Be part of a pioneering initiative in AI technology.
• Work on projects that center around real-world representation.
• Collaborate with passionate and mission-driven teams.