Senior Machine Learning Engineer, Generative Models

Summary

Join Splice as a Senior Machine Learning Engineer and contribute to pushing the boundaries of artificial intelligence applied to audio data. Design cutting-edge model architectures for generative audio/music applications, collaborate with other researchers, and explore core building blocks in generative models.

Requirements

• Master's or PhD degree in Electrical Engineering, Computer Science or related Engineering discipline
• Proven ability and track record designing, training, evaluating and deploying machine learning models in production environments, powering real applications
• 2+ years of hands-on experience with generative models architectures in the audio, image or language domains. Specific experience with Latent Diffusion Models and Transformer-based architectures is a must
• Proficiency in Python, C/C++, or CUDA. Strong proficiency in machine learning frameworks (e.g., TensorFlow, PyTorch)
• Hands-on experience with cloud services (e.g., AWS, Azure, GCP) and containerization technologies (e.g., Docker, Kubernetes)
• Comfortable with software development best practices and version control systems (e.g., Git)

Responsibilities

• Design, adapt and optimize cutting-edge model architectures for generative audio/music applications, leveraging state-of-the-art deep learning techniques for audio/music synthesis
• Collaborate with other Applied Researchers and Machine Learning Engineers to design, train, fine-tune, and deploy scalable models to production
• Explore and implement core building blocks in generative models, such as general Variational Autoencoders (VAEs), Neural Audio Codecs (RVQ / VAE), GANs, Diffusion Models, and Transformer-based architectures
• Contribute to integrating machine learning models into Splice’s products, delivering new and creative experiences for music creators
• Performance Benchmarking and Evaluation: design and run experiments to benchmark the accuracy, quality and performance of trained models
• Stay current with the latest advancements in machine learning applied to generative models in the audio domain, incorporating and sharing relevant insights into the applied research process
• Documentation and Knowledge Sharing: document experiments, best practices, and lessons learned to facilitate knowledge sharing and maintain reproducibility. Provide technical guidance and training to team members on model training, evaluation, deployment and optimization techniques