Java Developer at AI Studio Yandex Cloud

We are developing AI Search — a set of technologies within the AI Studio platform. Our tools allow models to generate responses based on strictly verified data, whether it be corporate documents or the external internet.

The system provides two key tools that can operate simultaneously:

• File Search — search through a user's own data (instructions, PDFs, FAQs)
• Web Search — search through selected domains on the internet

Our solutions are used to create voice agents (via Realtime API) and text bots (Responses API).

Our goal is to ensure that only the necessary, verified, and up-to-date information enters the model's context, and to ensure high-quality RAG (Retrieval Augmented Generation).

We are looking for a strong engineer who is ready to design architecture for complex enterprise solutions and adapt classic Java development to the dynamic requirements of the AI industry.

About the Team

More about our team - https://yandex.ru/jobs/services/cloud/ml

What Tasks Await You

Enterprise Backend Development You will create a reliable server-side in Java with complex business logic for orchestrating search agents.

Architecture and API You will design convenient, extensible, and secure REST and gRPC interfaces through which external clients interact with AI Search.

Optimization and Algorithms You will need to solve problems related to speeding up data search and filtering. You will have to find ways to optimize the system considering constraints (latency, model context window, load).

Adaptation of AI Solutions Your tasks will include implementing new approaches, as well as integrating with modern models.

More about backend at Yandex — in the channel Yandex for Backend

We Expect That You

• Have experience in industrial Java development
• Have optimized performance: know how to profile code, find bottlenecks, optimize memory and CPU usage
• Are familiar with basic algorithms and data structures, and can apply them to solve performance problems, not just for interviews
• Know how to design service architecture so that it is maintainable and scalable
• Are responsible, adaptable, and able to quickly immerse yourself in new technologies (the ML/AI field changes very rapidly)

Will Be a Plus

• Have built RAG platforms
• Have worked with search engines or semantic search technologies