AWS AI & Data Engineer - Remoto 100%
Summary
Design and develop data pipelines, semantic layers, and knowledge bases using AWS, Python, and graph databases to support AI-driven systems and LLM integration.
Data Engineer – AI & Data
At Alvea Soluciones Tecnológicas, we are looking for a Data Engineer to join an innovative AI & Data project, contributing to the design and development of data solutions, semantic layers, and knowledge bases that support AI-driven systems.
Responsibilities
· Design and develop data pipelines to integrate structured and unstructured data sources.
· Build knowledge models, taxonomies, ontologies, and semantic structures for AI-driven solutions.
· Work with relational databases, graph databases, and semantic/vector search technologies.
· Design and evolve RAG pipelines, semantic search capabilities, metadata enrichment, and natural language data access solutions.
· Work with AWS services such as S3, Glue, Aurora PostgreSQL, Neptune, and Bedrock.
· Develop query strategies using SQL, Gremlin, SPARQL, and/or Cypher.
· Implement data quality, monitoring, traceability, and data governance practices.
· Collaborate on integrating data layers with AI agents, LLM-based systems, and other AI solutions.
Requirements
· Proven experience in Data Engineering, Software Engineering, or AI Engineering within production environments.
· Strong Python and SQL skills.
· Experience designing and operating ETL/ELT pipelines in cloud environments.
· Experience with data modeling, taxonomies, ontologies, or knowledge representation.
· Knowledge of graph databases and query development using Gremlin, SPARQL, and/or Cypher.
· Experience with AWS services, especially S3, Glue, and Aurora PostgreSQL. Knowledge of Neptune and Bedrock is highly valued.
· Familiarity with RDF, OWL, SKOS, or similar knowledge representation standards.
· Experience with Docker, Git, and CI/CD practices.
· Knowledge of data quality, governance, metadata management, and data lineage.
Nice to Have
· Experience with LangChain, LangGraph, LlamaIndex, or similar LLM orchestration frameworks.
· Knowledge of RAG, vector search, and hybrid retrieval architectures.
· Experience with Kubernetes, Terraform, and DevOps practices.
· Knowledge of OCR, document processing, or multimodal AI solutions.
· Experience working in regulated environments with auditability and traceability requirements.
What We Offer
· Permanent contract.
· Opportunity to join an innovative project within the AI & Data space.
· Dynamic and collaborative working environment.
· Professional development and career growth opportunities.