Software Engineer, Real-Time Text-to-Speech (Pyhon/AI)

About the RoleWe are seeking a talented and passionate Software Engineer to join our innovative AI team. In this role, you will be at the forefront of developing our next-generation, real-time text-to-speech (TTS) engine. You will be responsible for the end-to-end lifecycle of our speech synthesis models, from researching the latest techniques to deploying and optimizing them for low-latency, high-performance applications. If you are passionate about building scalable AI solutions and have a knack for optimizing systems for efficiency, we would love to hear from you.What You'll DoResearch & Development: Investigate, implement, and evaluate state-of-the-art algorithms in speech synthesis and deep learning to continuously improve the naturalness and quality of our TTS voices.Model Optimization: Profile, quantize, and optimize deep learning models for high-throughput, low-latency inference on our server infrastructure.Deployment & MLOps: Design, build, and maintain robust, scalable backend services and APIs for our real-time TTS engine. Implement and manage CI/CD pipelines for model training and deployment.System Design: Collaborate with a cross-functional team of engineers and researchers to design and build a highly efficient, end-to-end TTS system.Code Quality: Write clean, well-documented, and rigorously tested code in Python and other relevant languages.Performance Monitoring: Develop tools and dashboards to monitor the performance, latency, and resource utilization of our production TTS services.