Senior Data Engineer (Python / GenAI) | Kraków, hybrid

An international team building advanced data integration and retrieval solutions powering Generative AI across the organization, focusing on AI agents, RAG pipelines, and large-scale GenAI applications.

• 5+ years of experience in software or data engineering with strong focus on Python.
• Hands-on experience with FastAPI, microservices and API-driven architectures.
• Experience with databases and data platforms such as MongoDB, PostgreSQL, Hadoop, BigQuery, Starburst or similar.
• Understanding of vector stores, embeddings or semantic search concepts.
• Experience working with cloud platforms (GCP or Azure).
• Solid understanding of Unix/Linux environments.
• Strong debugging skills and ability to clearly communicate findings.

Nice to have:

• Experience with RAG pipelines, context engineering or evaluation systems.
• Knowledge of Google ADK or similar AI development toolkits.
• Experience with memory stores or caching systems.
• Exposure to GenAI platforms, LLM-based solutions or AI agents.
• Familiarity with DevOps practices and CI/CD pipelines.

• Design and develop data integration components enabling GenAI models to access and process data from multiple internal systems.
• Build and maintain data transfer pipelines ensuring scalability, reliability and security.
• Develop Python-based microservices (FastAPI) integrated with broader GenAI platforms.
• Work with vector stores, memory stores and RAG pipelines to optimize data retrieval and context generation for AI agents.
• Collaborate with cross-functional teams to align data integrations with overall GenAI architecture.
• Implement monitoring, observability and performance tuning for data services.
• Participate in Agile ceremonies: sprint planning, reviews, retrospectives and daily stand-ups.