Knowledge Graph Data Engineer for GenAI Platform

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

Benefits offered by this job

Competitive salary

Comprehensive benefits

Mentorship and growth programs

Job summary

McKinsey & Company is seeking a data engineering professional to build graph-centric data pipelines and a semantic layer powering GenAI applications. You will design entity models, map diverse sources to graph schemas, and ensure scalable data services using Python, AWS, and Docker in a fast-paced environment.

Responsibilities include implementing ingestion and enrichment, performing entity resolution, and deploying production-grade code with CI/CD.

Qualifications

• Degree in CS/Engineering or equivalent experience.
• 3+ years of relevant experience with data engineering and cloud-based data pipelines.
• Experience with AWS services and knowledge graphs.
• Expertise in Python development with relational databases; strong testing practices.

Responsibilities

• Build graph-centric data pipelines and a semantic data layer for GenAI applications.
• Design and evolve entity/relationship models, taxonomies, and identifiers; map sources to graph schemas.
• Implement ingestion, normalization, and enrichment; perform entity resolution and semantic tagging.
• Write production-grade Python code; create CI/CD pipelines; operate AWS and Docker-based infrastructure.

Skills

Data engineering

Python development

AWS

Knowledge graphs

Docker

Relational databases

Generative AI interest

Problem solving

Communication

Team collaboration

Education

Degree in CS/Engineering or equivalent

Tools

Docker

Kedro

Job description

McKinsey & Company is seeking a data engineering professional to build graph-centric data pipelines and a semantic layer powering GenAI applications. You will design entity models, map diverse sources to graph schemas, and ensure scalable data services using Python, AWS, and Docker in a fast-paced environment.

Responsibilities include implementing ingestion and enrichment, performing entity resolution, and deploying production-grade code with CI/CD.