Job Details

Runtime Developer for Alice. Designing Alice's architecture and developing a new runtime to support long and fast tasks. Requires experience in developing high-load services and knowledge of C++.

Alice is a complex, high-load service based on large language models. We aim to create a new unified homogeneous runtime that meets modern requirements and can support both long agent tasks and requests requiring an instant response. What tasks await you: • Designing Alice's architecture You will be designing Alice's architecture and developing a new runtime so that Alice can work uniformly with both long tasks lasting tens of minutes and fast requests in hundreds of milliseconds without unnecessary overhead. The runtime will allow for improvements to the system as a whole and individual components (models, tools, agents), and trajectories will be written in unified terms.

We expect you to: • Be able to develop high-load services • Know the intricacies of asynchronous interaction in multi-component systems • Understand how agents work • Be ready to write in C++ It will be a plus if you: • Have worked with Temporal or another orchestration system • Are interested in LLMs and understand how they work

It's easy to find like-minded people at Yandex – we have communities for professionals of various profiles, from developers to designers. And also – book and language clubs. These are not all the bonuses – the full list is here.