ML Developer for the Voice Quality Enhancement Team at Alice

ML Developer for the Voice Quality Enhancement Team at Alice

The Alice voice assistant can distinguish user commands even with loud background noise and music. This is made possible by noise and echo cancellation algorithms developed by our team. Our algorithms also process audio during calls via smart devices and the Telemost service.

We are actively developing neural network approaches and are looking for an experienced ML engineer to strengthen our team. We value experience in ML and are ready to teach you about working with audio.

For our work we have:

• Dozens of modern GPUs for experiments and colossal volumes of data.
• A platform for A/B testing and data labeling with support from professional analysts.
• Acoustic laboratories and an apartment where we record audio.

What tasks await you

Improving model quality You will experiment with architectures, data, and training schemes to make our noise and echo suppression models even better.

Model implementation and optimization Our models run on Yandex devices with Alice, as well as on users' smartphones and laptops. Performance efficiency is a key aspect. You will accelerate models at the level of architecture and parameter selection, as well as at the level of final implementation.

Creating and improving quality metrics We develop metrics that will be calculated on users' devices while preserving their privacy and will serve as an indicator of overall audio quality.

We expect you to

• Have worked in the DL field (e.g., with CV or NLP)
• Be well-acquainted with Python and have basic C++ skills
• Know PyTorch

It will be a plus if you

• Have deployed neural networks into production, especially on user devices
• Have worked with large volumes of data
• Have experience with classical digital signal processing
• Possess advanced C++ skills
• Are familiar with Yandex's internal infrastructure or cloud computing platforms (AWS, Azure, Google Cloud)
• Have experience in web development