Knowledge Graph Data Engineer – QuantumBlack, AI by McKinsey

Job ID: 110946

Atlanta

Boston

Chicago

New York City

Do you want to do work that matters, alongside supportive leaders who will help you grow faster than you ever thought possible? Are you a creative problem-solver who is energized by challenges? You’ve come to the right place.

YOUR IMPACT

As a Knowledge Graph Data Engineer, you will build graph-centric data pipelines and a semantic data layer that powers GenAI applications for EcliptOS. EcliptOS is McKinsey's AI Operating System: driving value creation from strategy to execution through agentic systems.

You’ll build a platform that will be deployed across regions, sectors and functions. Focusing on a distinctive combination of AI capabilities, domain expertise, and human judgement. Your work will be at the forefront of developing exciting technology for our firm.

You’ll design and evolve entity/relationship models, taxonomies, and identifiers; implement ingestion, normalization, and enrichment that maps heterogeneous sources to graph schemas; perform entity resolution and semantic tagging; validate structures; and publish data to graph stores.

You’ll write production-grade Python code with comprehensive tests, create and modify GitHub Actions CI/CD pipelines, and operate AWS- and Docker-based infrastructure to deliver reliable, scalable knowledge graph data services.

YOUR GROWTH

Driving lasting impact and building long-term capabilities with our clients is not easy work. You are the kind of person who thrives in a high performance/high reward culture - doing hard things, picking yourself up when you stumble, and having the resilience to try another way forward.

In return for your drive, determination, and curiosity, we'll provide the resources, mentorship, and opportunities you need to become a stronger leader faster than you ever thought possible. Your colleagues—at all levels—will invest deeply in your development, just as much as they invest in delivering exceptional results for clients. Every day, you'll receive apprenticeship, coaching, and exposure that will accelerate your growth in ways you won’t find anywhere else.

When you join us, you will have

Continuous learning: Our learning and apprenticeship culture, backed by structured programs, is all about helping you grow while creating an environment where feedback is clear, actionable, and focused on your development. The real magic happens when you take the input from others to heart and embrace the fast-paced learning experience, owning your journey.

A voice that matters: From day one, we value your ideas and contributions. You’ll make a tangible impact by offering innovative ideas and practical solutions, all while upholding our unwavering commitment to ethics and integrity. We not only encourage diverse perspectives, but they are critical in driving us toward the best possible outcomes.

Global community: With colleagues across 65+ countries and over 100 different nationalities, our firm’s diversity fuels creativity and helps us come up with the best solutions for our clients. Plus, you’ll have the opportunity to learn from exceptional colleagues with diverse backgrounds and experiences.

World-class benefits: On top of a competitive salary (based on your location, experience, and skills), we provide a comprehensive benefits package to enable holistic well-being for you and your family.

YOUR QUALIFICATIONS AND SKILLS

Degree in CS/Engineering or equivalent experience

3+ years of relevant experience which may include a combination of professional work experience and relevant education

Data engineering experience, with a strong focus on cloud-based data engineering using AWS services; Previous enterprise platform experience preferred

Expertise with Python development with strong experience with relational databases

Experience with knowledge graphs

Practicing high coding standards with clean code, modularity, error handling, testing automation and more

Very driven, super strong on execution and output orientation, likes to get job done attitude and ability to figure things out independently. Able to work in a complex and very fast paced environment

Hands-on experience with Docker

Solid and demonstrable background in data pipeline performance and diagnostics

Interest in Generative AI and other ML topics. Kedro framework experience as a plus

Excellent problem-solving skills and the ability to analyze and resolve complex data engineering challenges

Strong communication and collaboration skills, with the ability to work effectively in a cross-functional team environment

Please review the additional requirements regarding essential job functions of McKinsey colleagues.

Our unwavering commitment to integrity drives everything we do, guiding us to always act in the best interests of our clients, our people, and the communities we serve.