tldr: Senior LLM Engineer at a large bank. Internal AI Platform, open-source LLM, agents/RAG. Hybrid, Moscow.

[no salary range, but the vacancy passed a vote with high trust in the author, funds are available]

We in the CIB LLM Team are responsible for the AI Platform for the bank's corporate business: LLM API Gateway, AI Chat, agent solutions, infrastructure for models and agents, tools for creating AI products.

We are looking for an LLM engineer to strengthen our team in the area of internal AI products, agents, RAG, and inference optimization.

What to do:

• be responsible for the internal AI Platform and tools for AI applications;
• design agents for business process automation;
• work with RAG, tool calling, and corporate knowledge;
• optimize inference quality, cost, and latency;
• participate in the selection and operation of open-source LLMs;
• bring hypotheses and prototypes to production.

What is important:

• confident Python;
• 2+ years of ML/DL experience;
• understanding of modern LLM/NLP/GenAI;
• experience with LLM-based production systems;
• understanding of retrieval, routing, tool calling, memory, evaluation;
• experience with Docker/Kubernetes and microservice architecture.

Will be a plus:

• deep understanding of LLM system evaluations;
• experience in self-hosted inference;
• experience in industrial development.

We offer:

• the opportunity to work on an AI Platform for a large corporate business;
• work on products used daily by bank employees;
• a strong engineering team, autonomy, and influence on architecture;
• the opportunity to work with modern open-source models and a GPU cluster;
• Voluntary Medical Insurance, training, conferences, hybrid work, and an office in the center of Moscow.

To apply: send your resume to Kamila — @kamila_bgsh