GenAI Knowledge Graph Engineer

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

Job summary

McKinsey & Company in the United States is seeking a data engineer to build graph‑centric data pipelines and a semantic data layer powering GenAI applications. You will design entity models and map diverse sources to graph schemas, delivering scalable knowledge services.

The role emphasizes production‑grade Python, CI/CD with GitHub Actions, and operating AWS and Docker infrastructure, enabling fast, reliable delivery and broad impact across regions.

Qualifications

• Degree in CS/Engineering or equivalent experience.
• 3+ years of relevant experience in data engineering.
• Cloud-based data engineering using AWS services; enterprise platform experience preferred.
• Expertise with Python development and relational databases.
• Experience with knowledge graphs.
• High coding standards: testing, modularity, error handling, tests.
• Hands-on experience with Docker.
• Strong execution orientation and ability to work in fast-paced environments.
• Kedro framework experience is a plus.
• Excellent problem-solving and cross-functional collaboration skills.

Responsibilities

• Build graph-centric data pipelines and a semantic data layer powering GenAI applications.
• Design and evolve entity/relationship models and taxonomies.
• Implement ingestion, normalization, and enrichment mapping sources to graph schemas.
• Perform entity resolution and semantic tagging; validate structures.
• Publish data to graph stores; write production-grade Python code and tests.
• Create/modify GitHub Actions CI/CD pipelines and operate AWS/Docker infrastructure.

Skills

Data engineering

Python development

Knowledge graphs

Problem solving

Cross-functional collaboration

Communication

Data modeling

Testing automation

CI/CD

GitHub collaboration

Education

Degree in CS/Engineering or equivalent experience

Tools

Docker

GitHub Actions CI/CD

AWS services

Job description

McKinsey & Company in the United States is seeking a data engineer to build graph‑centric data pipelines and a semantic data layer powering GenAI applications. You will design entity models and map diverse sources to graph schemas, delivering scalable knowledge services.

The role emphasizes production‑grade Python, CI/CD with GitHub Actions, and operating AWS and Docker infrastructure, enabling fast, reliable delivery and broad impact across regions.