端侧豆包大模型工程专家（嵌入式AI/端到端语音方向） - Data语音
Core
Designing, architecting, and engineering end-to-end voice AI models for smart hardware devices to enable real-time voice interaction and innovative agent products.
Role type
Senior Embedded AI Engineer (End-to-End Voice)
Builds
End-to-end voice interaction solutions, on-device voice agents, and optimized runtime environments for smart speakers, wearables, and robots.
Domain
Consumer Electronics / Embedded Systems / Large Language Models
Deliverable
production ML models
Required skills
C programming, Linux/Android/RTOS system development, hardware interface drivers (SPI/I2S/GPIO/I2C), ARM/DSP/MCU platforms, multi-threading and process scheduling, memory and power optimization.
Preferred skills
Smart hardware product launch experience, audio/video development experience.
Responsibilities
Design and implement voice model architectures for edge devices, optimize runtime performance for latency and power consumption, develop hardware-software co-optimization links, and drive end-to-end product delivery from concept to mass production.
Seniority
Senior, hands-on IC
