Remote Data Engineer: AI-Driven Pipelines & Graphs

Description Ciklum; Town of Poland (NY); On-site; USD 48,000 - 64,000; Full time

Benefits offered by this job

Udemy access

Language courses

Company-paid certifications

Luxmed medical package

Job summary

Ciklum is hiring a Data Engineer to join a cross-functional team on a 26-week enterprise project in Poland. You will build and maintain data pipelines that transform codebase data into structured Markdown assets and JSON/RAG inputs, while ingesting graphs in Neo4j and vector indices in Qdrant.

You will collaborate with AI/ML engineers to optimize performance and ensure data accuracy. The role requires 3+ years in data engineering, strong Python/SQL skills, and experience with graph databases or

Qualifications

• 3+ years of commercial Data Engineering experience building and maintaining production data pipelines
• Solid proficiency in Python, SQL, and standard data manipulation frameworks
• Hands-on knowledge of graph databases (Neo4j), vector search engines (Qdrant), or static code parsing frameworks (Tree-sitter)
• Proficiency with Git version control, Docker, unit/integration testing for data pipelines, and CI/CD workflows
• Strong analytical skills with focus on data accuracy, schema consistency, and output validation
• Professional proficiency in English (B2+/C1)

Responsibilities

• Develop, test, and maintain robust data pipelines that process AST outputs, knowledge graphs, and vector embeddings
• Ingest, normalize, and update code dependency graphs in Neo4j and vector indexes in Qdrant
• Parse raw source code structures and metadata into structured Markdown assets and standardized JSON/RAG inputs
• Monitor execution throughput, resolve batch processing errors, and ensure data state consistency across pipeline runs
• Collaborate with Senior Data Engineers and AI/ML Engineers to optimize data retrieval speeds and pipeline efficiency

Job description

Ciklum is hiring a Data Engineer to join a cross-functional team on a 26-week enterprise project in Poland. You will build and maintain data pipelines that transform codebase data into structured Markdown assets and JSON/RAG inputs, while ingesting graphs in Neo4j and vector indices in Qdrant.

You will collaborate with AI/ML engineers to optimize performance and ensure data accuracy. The role requires 3+ years in data engineering, strong Python/SQL skills, and experience with graph databases or