Intern for developing AI agents based on large language models in the Sber ecosystem. Participation in the full cycle: from prototypes to production implementation.
Tasks:
- develop Proof of Concept and Minimum Viable Product of artificial intelligence agents based on large language models using frameworks (LangChain, GigaChain)
- analyze and adapt existing State of the Art practices
- participate in the full cycle of development and integration: from creating prototypes to production implementation and monitoring of solutions
- interact with applied and business teams within the Sber ecosystem
Requirements:
- current study in the final years of bachelor's, master's, or postgraduate programs at a technical university with a strong background in mathematics and algorithms
- strong knowledge of Python (NumPy, Pandas, PyTorch, basics of object-oriented programming, etc.)
- deep understanding of deep learning and classical machine learning
- practical experience with large language models, Retrieval-Augmented Generation, and relevant frameworks and databases (LangChain, FAISS, Qdrant) and a desire to develop in this area
- experience with development tools (bash, git), including team development experience or a desire to quickly acquire these skills
- ability to understand scientific publications and modern State of the Art solutions, formulate and promote own research hypotheses
Conditions:
- paid internship
- internship duration: 3 months, 40 hours per week or 6 months, 20 hours per week
- working hours: from 9:00 to 18:00
- hybrid work format with office visits at least 3 days a week
- comfortable modern office at: Moscow, Kutuzovsky Prospect, 32
- professional team (our center employs PhDs, postgraduates, and Kaggle masters)
- interesting tasks and active work with new technologies
Skills:
- Python
- NumPy
- Pandas
- PyTorch
- LangChain
- GigaChain
- FAISS
- Qdrant
- bash
- git
- Retrieval-Augmented Generation
- large language models
- deep learning
- machine learning
