Knowledge Graph Architect & Data Pipelines

Appnovation Technologies

Medellín, Bogotá

Presencial

COP 278.353.000 - 371.138.000

Jornada completa

Hace 4 días

Sé de los primeros/as/es en solicitar esta vacante

Recibe más respuestas de empleadores

Envía un currículum específico para el puesto de trabajo en cuestión de minutos.

Descripción de la vacante

Appnovation Technologies in Medellín, Colombia, is seeking a Data Architect/Engineer to own the data structures behind our graph-RAG platform and to design scalable ingestion pipelines from enterprise sources like SharePoint. You will define schema, taxonomy and graph models for our knowledge domains and ensure the knowledge graph remains accurate as sources evolve.

The role requires 5+ years in data engineering or architecture, deep data modeling across relational and graph paradigms (Neo4j,

Formación

Bachelor’s degree in Computer Science or related field.
5+ years in data engineering/architecture roles.
Deep data modeling across relational and graph paradigms; graph databases (Neo4j) and Postgres/Supabase at scale.
Strong ETL / data pipeline engineering in Python, including large-scale, incremental, and change-data ingestion.
Experience with enterprise content ecosystems: SharePoint, ideally Power Platform / Power Automate.
Knowledge representation, taxonomies/ontologies, and versioned/temporal data.
Understanding of how data structures feed RAG and LLM retrieval quality.
SQL proficiency; experience with orchestration tools (e.g., Airflow) and cloud data services.
Familiarity with data governance, security, and privacy practices.
Strong documentation and cross-team communication skills.

Responsabilidades

Define the schema, taxonomy, and graph modeling for the knowledge domains.
Design how documents, versions, and their machine-readable representations are structured, and how facts evolve over time (including temporal replay).
Build ingestion/ETL pipelines from enterprise content sources (e.g., SharePoint and the wider Microsoft stack), handling multimodal content (presentations, documents, transcripts).
Keep the knowledge graph in sync as source documents change frequently.
Advise on whether the current backend approach (Supabase/Postgres) is the right long-term architecture, and validate ingested content quality with QA.
Establish data quality, lineage, and governance standards across pipelines.
Build monitoring, alerting, and error-handling for ingestion jobs.
Document data models, schemas, and pipeline architecture.
Optimize pipeline cost, throughput, and reliability over time.