CareerPlanGet AI match score →

Deep Learning Engineer (음성 인식 및 wake word detection 개발)

Pangyo (Software Dream Center), South Korea💼 Full-time🗓 2025-04-06 → 2026-07-31

Core

Designing and optimizing next-generation voice interfaces for automotive environments, connecting user speech to LLM-based AI Agents via STT, Wake Word Detection, and On-device AI.

Role type

Senior IC Deep Learning Engineer (Speech AI)

Builds

Production STT and Wake Word Detection models, optimized for Linux and Android devices

Domain

Automotive AI, Speech Recognition, Edge Computing

Deliverable

production ML models

Required skills

Speech signal processing, STT model design, Wake Word Detection (WWD) model design, On-device application development (Linux/Android), C/C++/Python, Deep learning frameworks (PyTorch/TensorFlow/Keras/Caffe), Hardware-efficient model optimization

Preferred skills

SSL (Self Supervised Learning), AED (Attention based Encoder-Decoder), Multi-lingual STT, Language model research for speech recognition, Top-tier journal/paper publication, Master's/PhD in relevant field

Technologies

PyTorch, TensorFlow, Keras, Caffe, Linux, Android, Git, CI/CD

Responsibilities

Design STT acoustic/language models and build voice databases, Design WWD models and build voice databases, Develop batch/streaming voice applications for server and on-device, Develop hardware-efficient models and optimize performance

Seniority

Mid-level to Senior, hands-on IC

Sourced via ashby · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Ashby ↗