We are looking for a gifted Senior AI/LLM Python Engineer to join our product development team for a US-based client. The project involves integrating an intelligent multi-agent system and modernizing the RAG architecture to enhance user experience and automate support for both users and developers in a booking management application (e.g., for car service centers, beauty salons, clinics, etc.).
Responsibilities
- Design, develop, and deploy AI/LLM-powered backend systems and agents.
- Build and maintain event-driven architectures using WebSockets.
- Develop and optimize Retrieval-Augmented Generation (RAG) systems.
- Integrate AI agents into production backends, ensuring scalability and reliability.
- Collaborate with cross-functional teams to deliver high-quality AI solutions.
- Monitor, test, and improve AI agent performance and observability.
- Stay up-to-date with the latest advancements in AI, LLMs, and backend technologies.
Requitements:
- 5+ years of commercial software engineering experience.
- 1+ year of hands-on experience working with AI/LLM technologies.
- Strong proficiency in Python.
- Proven experience with backend development and production deployments.
- WebSockets and event-driven systems expertise.
- Demonstrated experience building Retrieval-Augmented Generation (RAG) systems.
- Experience deploying AI agents to production and exposing them through backend services.
Strongly Preferred
- Experience with AutoGen for AI agent development.
Nice to Have
- Experience with AI agent observability and testing.
- Familiarity with Qdrant or other vector databases.
- Knowledge of Neo4j or other graph databases.
- Functional understanding of frontend/backend interactions.
We offer friendly working conditions with competitive compensation and benefits including:
- Comfortable working environment
- Friendly team and management
- Free English classes
- Flexible working hours
- 100% paid vacation, 4 weeks per year
- 100% paid sick-leaves
- Corporate and team building events