Machine Learning Engineer (Audio Processing)

innovAI

Andorra, Spain
Permanent
Hybrid
€65,000 - €85,000/year
PyTorchAudio Signal ProcessingLibrosa

Role Overview

We are seeking a specialized Machine Learning Engineer with a focus on Audio Signal Processing to join our technical team in Andorra. In this role, you will be responsible for designing and implementing state-of-the-art algorithms for audio analysis, feature extraction, and sound classification. You will bridge the gap between digital signal processing (DSP) and modern deep learning frameworks to solve complex audio-related challenges.

Key Responsibilities

  • Develop and optimize machine learning models for audio processing using PyTorch.
  • Implement robust audio feature extraction pipelines utilizing Librosa and other DSP libraries.
  • Research and apply the latest techniques in sound classification, source separation, or speech enhancement.
  • Collaborate with data engineers to build scalable data processing pipelines for large audio datasets.
  • Deploy and maintain ML models in production environments, ensuring high performance and low latency.

Required Qualifications

  • 3+ years of professional experience in Machine Learning or Data Science.
  • Deep expertise in Python programming and the PyTorch ecosystem.
  • Proven experience with audio-specific libraries such as Librosa, Torchaudio, or Essentia.
  • Strong understanding of Digital Signal Processing (STFT, Mel-spectrograms, MFCCs).
  • Background in training and fine-tuning neural network architectures (CNNs, RNNs, Transformers).

Nice-to-Have

  • Experience with C++ for real-time audio processing.
  • Familiarity with cloud platforms (AWS/GCP/Azure).
  • Contributions to open-source audio or ML projects.