Senior AI Engineer with Graph (GraphRAG, Neo4J)

We are looking for aSenior AI Engineer with Data engineering experience for the team of our Fortune 50 client, building scalable, production-grade data and AI-enabled systems. The main objective of the role is to designand develop scalable data pipelines, backend services, and APIs as well as build knowledge graph solutions, including graph data modeling, relationship mapping, and graph traversal logic.

This is along-term remote-first contract positionwith a required overlap ofUS working hours (2-6 PM CET).

Responsibilities

• Build ETL pipelines

• Design data models.

• Design and implement GraphRAG solutions combining knowledge graphs, vector search, metadata, and LLM-based retrieval.

• Create Source to Target Mappings (STMs) for ETL specifications.

• Implement automated ingestionpatterns, incremental (delta) updates, and streaming/CDC workflows.

Collaboration & Agile Development

• Gather requirements, settargets, defineinterface specifications, and conductdesign sessions.

• Work closely withdata consumers to ensure proper integration.

• Adapt and learn in afast-paced project environment.

Work Conditions

• Type: Full-time & Long-term contract work

• Start Date: ASAP

• Location: Remote (99%) in Europe; must be able to travel freely within Europe for workshops.

• US Time Zone Overlap: Required (2 PM - 6 PM CET)

• Contract with European LLC

• Strong proficiency in Pythonbuilding backend services/APIs as well as data pipelines

• ETL, data modeling, and performance tuningexperience

• Experience with Neo4j,Cosmos DB or Gremlin API.

• Knowledge of GraphRAG, retrieval systems, LLMs, embeddingsand RAG pipelines.

• Hands-on GenAI experience: LangGraph (or similar), MCP, RAG, agentic memory management and other concepts

• Hands-on data experience withMicrosoft Fabric, Synapse, ADF, or similar cloud data stacks.

• Understanding of software engineering and testing practices within anAgile environment.

• Experience with Data as Code; version control, small and regular commits, unit tests, CI/CD, packaging, familiarity with containerization tools such as Docker (must have) and Kubernetes (plus).

• Excellent teamwork and communication skills.

• Proficiency in English, with strongwritten and verbal communication skills.

• Efficient, high-performance data pipelines for real-time and batch data processing.

Nice to have:

• Experience with Databricks or similar data platforms.

• Vector databases, Azure AI Search, or semantic search platforms.