Runtime Developer at Alice

Alice is a complex, high-load service based on large language models. Every year, Alice becomes smarter and helps users solve increasingly complex tasks. We are now increasingly using large language models (LLMs) for this.

Each model is good at a specific task, but training one universal model that perfectly solves all tasks is very difficult. Therefore, we are teaching models to work with each other, turning them into agents. Each agent specializes in something: one searches for information on the internet, another controls the browser, a third works with files or applications.

Alice consists of many components and runs on a large family of platforms. We want to create a new unified homogeneous runtime that will meet modern requirements and be able to support both long agent tasks and requests requiring an instant response.

What tasks await you

Designing Alice's architecture You will design Alice's architecture and develop a new runtime so that Alice can uniformly handle both long tasks lasting tens of minutes and quick requests in hundreds of milliseconds without unnecessary overhead. Alice must remain reliable, efficient, and scalable, handling tens of thousands of RPS. It works with various types of input data: files, images, voice, text. The runtime will allow improving the system as a whole and individual components (models, tools, agents), and trajectories will be written in unified terms. The architecture should be transparent and understandable.

We expect you to

• Be able to develop high-load services
• Know the nuances 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