Description
We develop agentic RAG systems that help the company improve customer experience through personalized solutions.
We already have a working product operating in production and delivering value. Currently, we are actively developing new use cases for the agent and improving the efficiency of the existing solution.
Responsibilities
- Adapt the current agent for new business directions
- Conduct experiments with pipeline components (retriever, reranker, generative part), improve the quality of search and LLM response generation
- Experiment with synthetic data for quality evaluation and model fine-tuning
- Collaborate with DE and product analysts to search for and test new data sources, including for specific cases
- Develop quality evaluation methodology, interact with annotators, configure llm-as-a-judge for specific cases
- Collaborate with MLE to deploy models/agentic solutions to production, focusing on their optimization and monitoring.
Requirements
- Experience in machine learning and NLP for 1+ years (Middle) / 3+ years (Senior)
- Knowledge, understanding of architectures and experience working with models such as GPT, BERT and their analogues
- Proficient in Python and ML stack (PyTorch, transformers) at the level of writing custom training and inference loops
- Experience successfully deploying NLP models to production and optimizing them (for Middle/Senior)
- Knowledge of big data fundamentals and experience processing it (Spark, Hadoop)
- Command of basic development toolset: bash, git, docker, etc.
- Skills in working with generative AI models; experience creating AI agents and utilizing them in work will be an advantage
- Experience using GigaChat, Kandinsky, and analogues in products, skills in creating and using AI agents
- Instrumental proficiency in AI for analysis, generation, and automation.
Conditions
- Comfortable, modern office near Kutuzovskaya metro station
- Work format - office
- Annual salary review, annual bonus
- Corporate gym and relaxation areas
- Over 400 educational programs from SberUniversity for professional and career development
- Extended private health insurance, preferential insurance for family, and corporate pension program
- Flexible mortgage discount, equal to 1/3 of the Central Bank key rate
- Free SberPrime+ subscription, discounts on products from partner companies
- Reward for recommending friends to join Sber's team.
