We are looking for a Data Integration Engineer (GenAI) to design, build, and maintain scalable data integration pipelines and high-performance microservices for Generative AI platforms. In this role, you will leverage Python and FastAPI to build real-time orchestration services, connect legacy enterprise data stores (Hadoop, Starburst, PostgreSQL, MongoDB) with Google Cloud Platform (GCP / BigQuery), and deploy low-latency Retrieval-Augmented Generation (RAG) solutions using vector stores like PGVector.
If you have a strong background in data engineering or Python backend development, hands-on experience with GCP and vector search, and want to build enterprise-grade AI data retrieval systems in a hybrid Kraków environment, we’d love to talk to you.
What will your tasks involve?
- Design and develop data integration solutions to support Generative AI platforms and applications
- Build agents that source and retrieve data from multiple enterprise systems for GenAI use cases
- Develop scalable data transfer pipelines to enable efficient movement and processing of data
- Design and implement Python based microservices using FastAPI
- Integrate structured and unstructured data sources into AI and analytics platforms
- Build and support Retrieval Augmented Generation RAG solutions and context aware AI services
- Develop data access and retrieval services leveraging vector databases and memory stores
- Work with cloud native services across Google Cloud Platform GCP and Azure
- Design solutions that support data virtualization data governance and enterprise scale AI workloads
- Collaborate with AI engineers platform engineers and data teams to enable GenAI solutions
- Ensure solutions are scalable secure reliable and production ready
- Contribute to evaluation frameworks context engineering and AI model performance improvements
What we expect from you?
- Core Experience: 5-7 years of experience in Data Engineering, Data Integration, or Backend Engineering
- Python & Microservices: Strong hands-on Python development experience, including FastAPI and microservices architecture
- Data Integration & Virtualization: Proven experience building enterprise data pipelines, with exposure to Big Data engines like Hadoop, Starburst (Trino), and data virtualization
- Databases & Cloud: Solid knowledge of relational and NoSQL databases (PostgreSQL, MongoDB) and hands-on experience with Google Cloud Platform (GCP & BigQuery)
- GenAI & Vector Stores: Understanding of Retrieval-Augmented Generation (RAG) architectures, Context Engineering, and experience working with Vector Databases (such as PGVector)
- Production Standards: Ability to deliver scalable, secure, reliable, and production-ready enterprise data solutions
- Collaboration: Strong problem-solving, data modeling, and communication skills to collaborate with cross-functional AI, platform, and data teams
What you can expect from us?
- Form of employment: B2B contract
- Hybrid Work Model: Balanced setup with 2-3 days per week in a modern Kraków office and core working hours from 9:00 AM to 5:00 PM CET
- High-Impact Enterprise Environment: Direct involvement in modernizing critical technology ecosystem, combining global banking stability with modern engineering standards
- Cutting-Edge Tech Stack & AI Innovation: Hands-on experience with Python, FastAPI, RAG, PGVector, microservices, and Google Cloud Platform (GCP & BigQuery)
- Global Collaboration & Engineering Culture: Work alongside AI engineers, platform engineers, and international stakeholders within a collaborative, cross-border delivery model
Employment agency entry number 47
this job offer is intended for people over 18 years of age
...