Description
We create intelligent digital solutions based on generative AI technologies, NLP, and modern approaches to working with corporate data. Our products are aimed at automating and improving the efficiency of employees' and clients' work. The AI agents we work on have the capability to conduct meaningful dialogue, solve complex tasks, understand the context of interaction, and flexibly adapt to various roles and usage scenarios. They are integrated into corporate systems and help users make informed decisions based on available company knowledge and data. We are expanding our team and looking for a middle-level developer who will help develop agent functionality, improve solution architecture, and take user interaction quality to the next level.
The first stage of selection for this vacancy is a conversation with an AI recruiter. After applying, you will receive an invitation via email and in the chat on the HeadHunter platform to take a preliminary interview with GigaRecruiter on Telegram. The dialogue will take about 10 minutes. Its goal is to clarify missing details and speed up the consideration of your candidacy.
GigaRecruiter is just starting its journey, so we ask for your understanding. Your experience and participation will help make it convenient and useful!
Responsibilities
- develop and implement AI agents based on LLMs (including GigaChat)
- design application architecture and pipelines for processing user requests
- participate in the creation and development of RAG systems (Retrieval-Augmented Generation)
- work with LLMs: write and optimize prompts (prompt engineering), manage interaction with the model
- integrate solutions with corporate systems, ensure their interaction
- write maintainable, readable code; participate in reviews, discussions, and the formation of technical approaches.
Requirements
- confident knowledge of Python (Generic, ABC, decorators) and OOP principles
- experience with libraries: transformers, LangChain, pandas, numpy, SQLAlchemy
- experience with FastAPI: SOLID, DRY, OOP, DI; Layered Architecture; Concurrency; Distributed Tracing; Fault Tolerance (backoff, tenacity); Build (poetry/uv); HTTP Errors; custom API clients; State Management
- practical experience in NLP: text vectorization, query classification, building RAG systems
- understanding of machine learning algorithms, knowledge of approaches to fine-tuning language models
- Git skills, experience in integrating solutions into production environments
- basic skills in working with databases (PostgreSQL) and in the Linux terminal
- ability to consider the user scenario and the value of the created functionality.
Conditions
- comfortable modern office near Kutuzovsky Prospekt metro station
- annual salary review and annual bonus
- corporate gym and relaxation areas
- more than 400 educational programs from SberUniversity for professional and career development
- onboarding program and supervisor assistance at the start
- extended VHI (Voluntary Health Insurance), preferential insurance for family, and corporate pension program
- flexible mortgage discount, equal to 1/3 of the Central Bank's key rate
- free SberPrime+ subscription, discounts on products from partner companies
- referral bonus for recommending friends to join the Sber team.
