We are looking to hire an ML expert with a significant amount of knowledge related to audio to research and develop novel algorithms and techniques to advance the state of the art in music information retrieval, source separation, and audio personalization.
We are looking for someone who can analyze and extract relevant information from petabyte amounts of structured and unstructured, complex and interrelated datasets related to audio using enterprise-level multi GPU systems.
Specifically we will be building highly advanced MIR models related to the following:
- Audio Classification (content type, instrumentation, genre/sub-genre, mood/character)
- Beat Tracking
- Chord Estimation
- Cover Song Identification
- Downbeat Estimation
- Fingerprinting
- Key Detection
- Melody Extraction
- Onset Detection
- Tag Classification
- Tempo Estimation
- Automatic Lyrics Transcription
- Drum Transcription
- Multiple Fundamental Frequency Estimation & Tracking, Music Detection
- Structural Segmentation
- Source Separation
Key Qualifications: Python, PyTorch, TensorFlow, or similar platforms.
Location: Remote
If interested please send an email to smith@mixed.com