Senior AI/ML Engineer with Audio Experience Offline

AI/ML Engineer Job Description

Responsibilities:

• Design and implement cutting-edge audio restoration tools, utilizing and expanding upon state-of-the-art techniques (e.g., diffusion models).
• Develop and deploy machine learning models for tasks such as audio classification, restoration, and sound separation.
• Work with PyTorch and C++ to integrate models into existing software frameworks.
• Optimize model performance for both compute resources and latency.
• Stay abreast of current research in audio and machine learning and implement relevant research papers.
• Collaborate with cross-functional teams to gather feedback and improve models and user experience.

Qualifications:

• Strong experience in training and fine-tuning diffusion models
• Comfort with taking on a project involving fine-tuning models similar to those found in https://github.com/multimodal-artprojection/YuE/tree/main
• Proven ability to design and implement machine learning models for audio processing tasks.
• Experience with PyTorch and C++
• Ability to optimize models for both performance and resource constraints
• Familiarity with current research in audio and machine learning
• Excellent collaboration and communication skills

Preferred:

• Experience with audio restoration and sound separation tasks
• Experience with deploying machine learning models in real-time applications
• Knowledge of audio processing techniques and tools