Description
We are the GigaChat Data team, preparing data for training the entire line of GigaChat LLM models (GigaChat, GigaChat Vision, GigaChat Audio, etc.). We specialize in creating and improving prompts (prompt engineering) that will help us develop our products, enhancing the quality of interaction between models and users.
Responsibilities
Tasks:
- development and optimization of complex system and user prompts
- integration of LLMs via API into product scenarios
- testing prompts, conducting experiments, and optimizing them according to quality metrics
- performing fact-checking and reviewing model responses, eliminating hallucinations, and improving style
- analyzing datasets, identifying and eliminating bottlenecks
- working in conjunction with AI trainers, ML engineers, analysts, and the product team.
Requirements
We expect from you:
- experience working with LLM APIs (GigaChat, OpenAI, Anthropic, local models, etc.)
- practical experience in creating and optimizing system and user prompts using various methods (few-shot, zero-shot, chain-of-thought, self-consistency, etc.), configuring generation parameters (temperature, top_p, max_tokens, etc.), and adapting prompts for different model use scenarios
- experience testing and evaluating prompts
- confident command of Python for automation (pandas, requests/httpx, working with JSON, data processing)
- understanding of RAG and tool-calling principles – ability to design and implement pipelines with retrieval-augmented generation; knowledge of approaches for integrating tools (tool-calling) to perform external functions, working with APIs
- understanding of LLM working principles, model training stages, and basic statistical metrics used in ML.
It will be a plus:
experience using GigaChat, Kandinsky, and analogues in products, skills in creating and using AI agents
- experience working with LangChain, GigaChain, or analogues
- skill in writing prompt generation and validation pipelines
- knowledge of English at the level of reading technical documentation.
Conditions
- remote work format for Nizhny Novgorod and the Nizhny Novgorod region
