Requirements
- Deep understanding of the architecture and principles of large language models (LLM).
- Experience in developing and integrating AI agents based on LLM and multi-agent systems.
- Understanding of fundamental methods and algorithms of machine learning and natural language processing (NLP).
- Experience with agent and task chain building tools (LangChain/GigaChain, LangGraph, LangFlow, n8n, Flowise, OpenRouter, NeuroAPI, GigaChat, ChatGPT, DeepSeek, Qwen, Mistral).
- Ability to design and deploy systems with RAG (Retrieval-Augmented Generation) and Knowledge Graph.
- Skills in prompt engineering to enhance model interaction quality.
- Experience in programming with Python (priority), Java / Go / JavaScript is a plus.
- Experience in creating and integrating backend services and WebUI for AI solutions.
- Knowledge of data exchange protocols: REST, WebSocket, JSON-RPC, gRPC.
- Experience with logging, monitoring, and diagnostics systems, including AI applications.
- Basic understanding of DevOps and CI/CD for deploying AI infrastructure.