Senior AI Data Engineer
Work Location: Remote
Work Mode: Remote
Notice Period: 0–30 Days
Experience: 5 to 8 years
Position Overview
We are looking for a highly skilled Senior AI Data Engineer specializing in Knowledge Graphs, GraphRAG, Retrieval-Augmented Generation (RAG), and AI Agent development to design, build, and deploy enterprise-grade AI solutions.
Key Responsibilities:
Have strong hands-on experience designing semantic layers and knowledge graphs
Have hands-on experience in developing domain ontologies using standards such as RDF, RDFS, and OWL.
Have hands-on experience in SPARQL
Have hands-on experience in working with complex enterprise data, implementing graph databases using Amazon Neptune
Have hands-on experience in migrating data from relational database to graph database.
Have hands-on experience in design and implement GraphRAG solutions that combine knowledge graphs, vector databases, and LLMs.
Have hands-on experience with Amazon Bedrock or other enterprise LLM platforms.
Have experience in developing AI agents that combine graph traversal, vector search, and Large Language Models (LLMs) to deliver accurate, contextual, and fact-based responses.
Have experience with ontology-driven reasoning, semantic validation, and rule-based knowledge representation.
Required Technical Skills
Knowledge Graphs: Graph modeling, entity and relationship identification, graph schemas, semantic modeling, and graph traversal.
Semantic Technologies: RDF, RDFS, OWL, ontology design, classes, properties, axioms, constraints, and semantic relationships.
Amazon Neptune: Hands-on graph database development, data loading, query development, optimization, and production implementation.
Graph Query Languages: Gremlin, openCypher, and/or SPARQL, aligned with the graph model used.
GraphRAG and RAG: Hybrid retrieval, vector search, graph-based retrieval, context construction, and grounded answer generation.
LLMs and AI Agents: Agent design, tool/function calling, orchestration, retrieval integration, and production deployment.
Vector Databases: Experience with a vector database or vector search engine and integration with a knowledge graph.
Programming: Strong Python development skills.
Data Validation: Practical experience with Pydantic or equivalent structured data validation frameworks.
Data Migration: Relational-to-graph transformation, schema mapping, relationship migration, data validation, and reconciliation.
Cloud Platforms: Hands-on AWS experience preferred; Azure experience is acceptable if supported by demonstrable AWS learning and implementation capability.
Production Engineering: Testing, deployment, performance optimization, monitoring, security, troubleshooting, and maintainability.
