Data Engineer (4102)

Ciklum

Що робити

Data Pipeline Execution: Develop, test, and maintain robust data pipelines that process AST outputs, knowledge graph structures, and vector embeddings
Knowledge Base Ingestion: Write data processing 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 raw metadata into structured Markdown assets and standardized JSON/RAG inputs
Pipeline Monitoring & Debugging: Monitor execution throughput, resolve batch processing errors, and ensure data state consistency across pipeline runs
Collaboration: Work closely with Senior Data Engineers and AI/ML Engineers to optimize data retrieval speeds and pipeline efficiency

Professional Experience: 3+ years of commercial Data Engineering experience building and maintaining production data pipelines
Core Technical Proficiency: Solid proficiency in Python, SQL, and standard data manipulation frameworks
Hands-on Stack Exposure: Direct working knowledge of graph databases (Neo4j), vector search engines (Qdrant), or static code parsing frameworks (Tree-sitter)
Engineering Best Practices: Proficiency with Git version control, Docker containerization, unit/integration testing for data pipelines, and CI/CD workflows
Problem-Solving & Detail Orientation: Strong analytical skills with a focus on data accuracy, schema consistency, and output validation