Senior Data Engineer: AI Pipelines & Graphs (Remote)

Ciklum; Town of Poland (NY); On-site; USD 48,000 - 81,000; Full time

Benefits offered by this job

Remote work option

Premium medical with Luxmed

Udemy access

Language courses

Company-paid certifications

MyBenefit platform

Conferences and workshops

Internal mobility

Job summary

Ciklum in Poland is seeking a Senior Data Engineer to join a cross-functional team on a 26-week enterprise initiative. You will engineer an AI-assisted pipeline to generate structured documentation from a large codebase, integrating Tree-sitter AST outputs with Neo4j graphs and Qdrant vector stores.

Collaborate with AI/ML engineers, ensure data quality, security, and traceability in a regulated environment, and deliver outputs aligned with strict KPIs.

Qualifications

• 5+ years of Data Engineering experience building production-grade pipelines.
• Experience with graphs, vector storage, and data integration.
• Proficiency in Python and modern data engineering toolkits.

Responsibilities

• Build and optimize high-throughput data pipelines and ETL/ELT workflows.
• Design and maintain Neo4j graph schemas for code dependencies.
• Integrate Tree-sitter AST outputs with vector embeddings (Qdrant).
• Ensure data lineage, integrity, and cross-reference tracking.
• Collaborate with AI/ML engineers to improve retrieval quality.

Skills

Python

ETL/ELT pipelines

Data engineering

CI/CD

English (C1+)

Tools

Docker

Kubernetes

Neo4j

Qdrant

Job description

Ciklum in Poland is seeking a Senior Data Engineer to join a cross-functional team on a 26-week enterprise initiative. You will engineer an AI-assisted pipeline to generate structured documentation from a large codebase, integrating Tree-sitter AST outputs with Neo4j graphs and Qdrant vector stores.

Collaborate with AI/ML engineers, ensure data quality, security, and traceability in a regulated environment, and deliver outputs aligned with strict KPIs.