Data Engineer (AI)

Quick Facts

• Focus on AI data engineering: embeddings, semantic search, vector search, metadata indexing
• Backend/data services integration via REST APIs
• Event-driven data processing using Kafka or Pub/Sub

Description

Join a project for a banking client as a Data Engineer (AI) working on AI-focused data pipelines and services. You will work with embeddings, semantic search, vector databases (especially Qdrant), REST APIs, and event-driven architectures. The role emphasizes strong data engineering fundamentals and growth in unstructured data and AI.

Responsibilities

• Build pipelines and services for processing data
• Implement vector search capabilities (embeddings, semantic search, metadata filtering, indexing)
• Develop REST API integrations (FastAPI preferred)
• Support event-driven architecture (Kafka or Pub/Sub)
• Work with Linux systems and relational databases (e.g., PostgreSQL)

Requirements

• Strong knowledge of Python and/or Rust
• Experience building data processing pipelines and data services
• Practical experience with vector databases, especially Qdrant
• Knowledge of embeddings, semantic search, metadata filtering, and indexing
• Experience with REST API; FastAPI is preferred
• Knowledge of event-driven architecture such as Kafka or Pub/Sub
• Good knowledge of Linux
• Knowledge of relational databases such as PostgreSQL

Benefits

• Long-term collaboration
• Benefits package (Multisport, private medical care, life insurance)
• Training budget
• Free English lessons
• Individual support from a dedicated company contact