About the job
Join Us and Engage in Exciting Work!
After completing a comprehensive onboarding process to familiarize yourself with the Toss data environment, you will be part of the Data Warehouse Team, undertaking the following responsibilities:
Develop a data quality platform that enhances table consistency, advances DQ rules, and establishes health check metrics. We aim to create a reliability management platform allowing all data users to work without questioning, 'Can I trust this data?'.
Enhance the GraphRAG pipeline. Build a knowledge graph construction pipeline that extracts entities by parsing ontology YAML, SQL, and code, followed by vector embedding for indexing in Elasticsearch, making Toss's data assets easily navigable for everyone.
Design and operate MSA architectures. Split necessary services for the ontology platform into microservices, ensuring each is designed, implemented, and operated reliably.
Develop AI agent infrastructure. Create a multi-agent workflow execution environment based on open-source agent frameworks like CrewAI. Establish an MCP Tool Registry and develop integration infrastructure with external MCP servers.
Build an early warning platform. Create a monitoring system that detects anomalies in data lineage, code, and trends, automatically performing alerts and analyses to identify issues before they escalate.
Develop a lineage tracking engine. Create a system that automatically analyzes the extent of impacts by parsing SQL to extract column-wise influence relationships, determining how far changes propagate.

