#vacancy #SA #systemanalyst #системный_аналитик #LLM #AI
Good afternoon.
Looking for a System Analyst for a banking project focused on developing products based on AI solutions for a multifunctional Platform.
Format: remote project.
I consider candidates from Moscow and Moscow Oblast ONLY.
💰Income: up to 250,000 RUB NET
Employment only via Individual Entrepreneur (IE).
**To apply **@Vikt0ria_IT
- At least 3 years of experience as a System Analyst;
- Proficiency in requirements gathering, analysis, and documentation;
- Knowledge of business process modeling notations and experience in diagram visualization (UML, BPMN, etc.);
- Understanding of architecture: knowledge of microservices and monolithic architecture fundamentals, understanding how system components interact;
- Experience with relational databases (DDL, DML);
- Understanding of integrations and APIs: knowledge of REST principles, JSON/XML data formats. API documentation in OpenAPI, AsyncAPI formats and ability to test endpoints independently using Postman or Swagger;
- Understanding of LLM and AI agent architecture: knowledge of Tool-use, Skills, MCP, A2A protocols;
- Knowledge of RAG principles and techniques: understanding of vector databases and semantic search;
- Prompt Engineering skills;
- Experience in quality assessment: understanding how to measure factual accuracy, relevance, and safety of LLM responses;
- Experience in preparing technical documentation;
- Excellent communication skills;
- Systems thinking, analytical approach to problem-solving, results orientation;
- Experience working in teams using agile software development methodologies.
An advantage for candidates would be:
- Experience in software development and debugging;
- Delivery Management: Release Management, identifying and resolving inter-team dependencies;
- Practical experience using low-code platforms for AI agent orchestration (n8n, LangFlow);
- Skills in using coding agents (Codex, Claude Code, Cursor, opencode, etc.);
- Skills in using SDD frameworks (OpenSpec, SpecKit, SuperPowers);
- Basic scripting skills (e.g., in Python) for automating quality assessment (log parsing, running test datasets through LLM API);
- Understanding of ML fundamentals (how embeddings differ from traditional full-text search, when model fine-tuning is needed, and when RAG is sufficient).
