Deep Learning Engineer (음성 합성 개발)
Core
Developing next-generation Text-to-Speech (TTS) technology for natural and rich voice experiences in various vehicle environments, connecting research to actual products and services.
Role type
Senior IC Deep Learning Engineer (TTS & Audio)
Builds
On-device and server-side TTS models, real-time streaming synthesis systems, and optimized inference pipelines for automotive applications.
Domain
Automotive / Audio AI / Deep Learning
Deliverable
production ML models
Required skills
TTS model development, model quantization, NPU/AI accelerator porting, TensorRT/ONNX optimization, audio signal processing, Linux development, Python/C++ programming, PyTorch
Preferred skills
Multilingual/multi-speaker TTS development, audio tokenization, hands-on model deployment on test equipment, research publication in top-tier venues, PhD in related fields
Technologies
PyTorch, TensorRT, ONNX, NPU, Linux, Python, C++, shell
Responsibilities
Optimize TTS models for on-device and server environments, port and optimize models for AI accelerators like NPU, develop real-time streaming synthesis systems, build and improve TTS data for generative models, analyze and resolve TTS model and service issues in mass production environments
Seniority
Senior, hands-on IC (via careerplan.io/jobs/c184cf35-51e2-4e80-87bc-579089f07472-deep-learning-engineer-at-42dot)
