Speech Processing ML Algorithm Engineer

What you'll do

• Design, train, and evaluate machine learning models for speech enhancement tasks.
• Develop algorithms for noise suppression, de-reverberation, echo suppression, and multi-microphone processing.
• Build models that meet strict low-latency and real-time constraints for shipping hardware.
• Implement streaming and causal processing techniques for real-time audio applications.
• Conduct speech quality evaluations using objective metrics and subjective listening tests.
• Perform data simulation and augmentation to support model training and evaluation.
• Translate early prototypes into production-ready models through cross-functional collaboration.
• Apply model efficiency techniques such as quantization-aware training or distillation.

What we're looking for

• MS or PhD in a computational science field or 3+ years of experience in ML for speech processing.
• Deep understanding of transformers, recurrent and convolutional neural networks for audio ML research.
• Experience designing, training, and evaluating models for noise suppression, dereverberation, source separation, or echo residual suppression.
• Experience building models for low-latency, real-time requirements including streaming and causal processing.
• Strong grounding in audio and speech signal processing fundamentals, such as STFT analysis/synthesis.
• Proficiency with PyTorch and Bash, including version control, code review, testing, and reproducible experiments.
• Working knowledge of speech quality evaluation metrics (e.g., PESQ, STOI, SI-SDR, DNSMOS) and subjective listening tests.
• Experience with adaptive filter prediction, model efficiency techniques, or high-performance cloud computing (preferred).