Hello team,
We’re looking for a Machine Learning Engineer with a strong background in audio signal processing to join our team on an exciting project focused on real-time live concert audio enhancement. 
This role involves selecting the best track from multiple sources, reducing noise, and improving audio quality for live streaming. If foundation models aren’t available, you should be comfortable building custom ML models from scratch.
Key Responsibilities
• Build ML models for audio enhancement & source selection
• Design low-latency inference pipelines for real-time use
• Feature extraction using STFT, Mel Spectrograms, Wavelets
• Optimize models for streaming performance
• Work with Python, PyTorch/TensorFlow, AWS (S3, Lambda, IVS, SageMaker)
• Apply latest research (e.g., arXiv:2408.17434)
• Collaborate with audio engineers & streaming teams
Requirements
• Proven deep learning + audio signal processing experience
• Real-time, low-latency audio processing knowledge
• Strong Python + PyTorch/TensorFlow skills
• Familiarity with live-streaming & multi-source mixing
• Understanding of reverberation, spectral analysis, audio quality
• Bonus: Multi-mic, spatial audio, adaptive filtering, music production exposure
Location: Remote
Type: Freelance
Attachments: Share your GitHub, portfolio, or research links if available
If interested, reach out via DM or email duraimurugan.i@meyicloud.com
Please refer someone you know or share this in any relevant communities. Let’s push the boundaries of live audio with ML! 