Design and train state-of-the-art machine learning models for automatic speech recognition and wakeword detection
Job Summary
Design and train state-of-the-art machine learning models for automatic speech recognition and wakeword detection.
Define and implement the data strategy for training and testing, as well as audio augmentation to reflect the far-field acoustic conditions of our products.
Collaborate with the cloud backend and embedded engineering teams to ensure our models perform the best they can in the different environments.
Matching Summary
Design and train state-of-the-art machine learning models for automatic speech recognition and wakeword detection.
Skills & Requirements
Must-have
state-of-the-art machine learning models
Automatic Speech Recognition (ASR)
wakeword detection
speech processing
Python and PyTorch
data strategy
training and evaluation pipelines
Nice-to-have
real-time, low latency, streaming ASR
model adaptation techniques
far-field ASR challenges
MLOps and software engineering
Key Requirements
8+ years experience in ML research & engineering for voice applications
PhD or Master’s degree in computer science or related field
In-depth knowledge of speech processing (ASR, wakeword detection, audio features)
Experience owning the whole model development lifecycle
Intermediate knowledge of a low-level compiled language (Rust, C, C++)