data engineer for AI systems
Posted Updated
act digital designs semantic data layers and knowledge base solutions that power enterprise-scale artificial intelligence systems.
Puede obtener más detalles sobre la naturaleza de esta vacante y lo que se espera de los solicitantes leyendo la información a continuación.
Задачи
- Design graph schemas, entity resolution strategies, ontological structures, and semantic indexing systems to support agentic AI
- Ingest and transform structured and unstructured data from S3, SharePoint, FileNet, and other sources while ensuring semantic consistency
- Create taxonomies and ontologies using RDF, OWL, and SKOS standards
- Operate and orchestrate AWS services including S3, Glue, Aurora PostgreSQL, Neptune, and AWS Bedrock
- Build RAG pipelines, semantic search, metadata enrichment, and Text-to-SQL interfaces
- Design graph retrieval strategies combining pattern matching, vector search, full-text search, and relational traversals
- Ensure quality control, monitoring, and production readiness of AI data infrastructure
- 4–5 Years of experience in Data Engineering, Software Engineering, or AI Engineering with solutions deployed in production
- Advanced Python (P3 - Advanced) and SQL proficiency
- Practical experience modeling and developing queries with Gremlin, SPARQL, and/or Cypher
- Solid AWS experience with S3, Glue, and Aurora PostgreSQL
- Experience designing batch and incremental ETL/ELT pipelines
- Experience with Docker, CI/CD, and Git
- Experience with hybrid retrieval xqbhyrx architectures combining SQL, graph, and vector search
- Knowledge of data lineage, cataloging, metadata management, and data quality frameworks
- Degree or Master's in Computer Science, Mathematics, Physics, Engineering, or a related field
- Spanish at C1 (Expert) level
- English at B2 (Advanced) level
- Nice to have: Neptune and AWS Bedrock
Hybrid schedule with 40% telework / remote work; Office schedule.