Data Engineer — Remote AI Pipelines & Knowledge Graphs

Ciklum; Poland; On-site; PLN 180,000 - 240,000; Full time

Benefits offered by this job

Luxmed medical package

Udemy access

MyBenefit platform

Job summary

Ciklum is looking for a Data Engineer to join our team in Poland on a full-time basis. You will work on a cross-functional project to engineer automated documentation pipelines from a large codebase using Tree-sitter, Neo4j, and Qdrant.

Ideal candidates have 3+ years in data engineering with Python/SQL, experience with graph databases and vector search, and strong CI/CD practices. Remote work options are available as part of a flexible, multinational engineering culture.

Qualifications

• 3+ years of commercial Data Engineering experience building and maintaining production data pipelines.
• Proficiency in Python and SQL; strong data manipulation skills.
• Hands-on experience with graph databases (Neo4j), vector search engines (Qdrant), or static code parsing (Tree-sitter).
• Strong Git usage, Docker containerization, unit/integration testing for data pipelines, and CI/CD workflows.
• Excellent problem-solving skills with a focus on data accuracy and schema consistency.
• Professional English (B2+/C1).

Responsibilities

• Data Pipeline Execution: Develop, test, and maintain robust data pipelines that process AST outputs, knowledge graphs, and vector embeddings.
• Knowledge Base Ingestion: Write scripts to ingest, normalize, and update code dependency graphs in Neo4j and vector indexes in Qdrant.
• Data Cleansing & Transformation: Parse raw source code structures and metadata into structured Markdown assets and JSON/RAG inputs.
• Pipeline Monitoring & Debugging: Monitor throughput, resolve batch errors, ensure data state consistency across runs.
• Collaboration: Work with Senior Data Engineers and AI/ML Engineers to optimize data retrieval speeds and pipeline efficiency.

Skills

Python

SQL

Neo4j

Qdrant

Tree-sitter

Git

CI/CD

Testing

English proficiency

Tools

Docker

Job description

Ciklum is looking for a Data Engineer to join our team in Poland on a full-time basis. You will work on a cross-functional project to engineer automated documentation pipelines from a large codebase using Tree-sitter, Neo4j, and Qdrant.

Ideal candidates have 3+ years in data engineering with Python/SQL, experience with graph databases and vector search, and strong CI/CD practices. Remote work options are available as part of a flexible, multinational engineering culture.