GenAI Knowledge Graph Engineer

McKinsey & Company, Inc.; Atlanta (GA); On-site; USD 138,000 - 142,000; Full time

Benefits offered by this job

Continuous learning

A voice that matters

Global community

World-class benefits

Job summary

McKinsey & Company is seeking a Knowledge Graph Data Engineer to build graph-centric data pipelines and a semantic data layer powering GenAI applications for EcliptOS, McKinsey's AI Operating System. You will design entity/relationship models, perform ingestion/normalization, and publish data to graph stores using Python, Docker, and AWS-based infrastructure.

You will work across regions and functions, applying solid coding standards, testing, and CI/CD practices while collaborating with跨

Qualifications

• Degree in CS/Engineering or equivalent experience.
• 3+ years of relevant experience including education.
• Data engineering with cloud-based AWS services; enterprise platform experience preferred.
• Expertise with Python development and relational databases.
• Experience with knowledge graphs.
• Practicing high coding standards with testing automation.
• Very driven with execution focus in fast-paced environment.
• Hands-on experience with Docker.
• Background in data pipeline performance and diagnostics.
• Interest in Generative AI; Kedro is a plus.
• Strong problem-solving and cross-functional collaboration skills.

Responsibilities

• Build graph-centric data pipelines and a semantic data layer for GenAI applications.
• Design and evolve entity/relationship models, taxonomies, and identifiers.
• Implement ingestion, normalization, and enrichment mapping sources to graph schemas.
• Publish data to graph stores and maintain production-grade Python code and CI/CD pipelines.

Skills

Python development

Data engineering

AWS cloud services

Knowledge graphs

Problem solving

Communication

Education

Degree in CS/Engineering or equivalent

Tools

Docker

Kedro

GitHub Actions CI/CD

SQL/Relational DBs

Job description

McKinsey & Company is seeking a Knowledge Graph Data Engineer to build graph-centric data pipelines and a semantic data layer powering GenAI applications for EcliptOS, McKinsey's AI Operating System. You will design entity/relationship models, perform ingestion/normalization, and publish data to graph stores using Python, Docker, and AWS-based infrastructure.

You will work across regions and functions, applying solid coding standards, testing, and CI/CD practices while collaborating with跨