Audio Algorithm Engineer (AI) | Master / PhD Holder
Core
Develop and deploy AI models for far-field audio processing, including speech recognition, voice interaction, and sound event detection, on embedded camera devices.
Role type
Senior IC audio algorithm engineer (AI)
Builds
Streaming speech recognition, voice interaction, and audio understanding models for smart security cameras
Domain
Consumer electronics / Audio AI / Embedded systems
Deliverable
production ML models
Required skills
Deep learning for audio, audio signal processing, speech recognition, voice activity detection, model compression, Python, PyTorch
Preferred skills
Far-field audio experience, on-device deployment, voice agents, audio-visual models
Technologies
Whisper, Parakeet, Qwen3-ASR, PyTorch, ONNX, TFLite, sherpa-onnx
Responsibilities
Develop streaming multilingual speech recognition and keyword spotting; Implement voice activity detection and turn-taking logic; Build noise suppression and echo cancellation pipelines; Train and evaluate sound event detection and audio captioning models; Optimize models for real-time inference on camera chips; Manage audio data pipelines and synthetic mixing
Seniority
Senior, hands-on IC
