Job Details

ML Engineer for a delivery robot development team. Develop and adapt ML methods, optimize models for computational constraints, and enhance the pipeline and ML models for autonomous transport. Requires experience in ML algorithm development and profiling...

A new technical direction is launching within the robot delivery division. Our goal is to significantly enhance the capabilities of delivery robots. To achieve this, we need to solve fundamentally new problems and develop innovative approaches across various areas of autonomous transport. We are seeking a strong developer to join a team that will guide the product from initial prototypes to a mature solution. What tasks await you: • Development and Adaptation of New Approaches Adapt new ML methods to the robot being developed, create approaches based on them, and conduct thorough training, including data selection, cleaning, setting up training pipelines, and analyzing results. • Adapting Algorithms to Computational Constraints Fit all models within limited memory and performance. We use various methods for model quantization, architecture optimization, and knowledge transfer. • Pipeline and ML Model Development Study and improve the vector map construction pipeline, develop and train ML models for extracting and vectorizing road infrastructure elements. Research and implement new approaches from scientific papers, propose and implement your own ideas and algorithms. Work with real autonomous transport data, participate in the full R&D cycle, analyze model quality, and influence safety and reliability metrics.

We expect you to: • Have developed ML algorithms from data collection to product deployment • Possess broad knowledge in ML methods, especially in robotics (localization, route planning, recognition) • Have experience in profiling and adapting neural network algorithms for platforms with limited computational power (quantization, pruning, Transfer Learning) It will be a plus if you: • Are familiar with classical ML methods

Yandex employees attend relevant conferences free of charge. And for those who present at them, we have a speaker training school. These are not all the bonuses – the full list is here.