Senior Data Scientist - Data Modeling & Quality

About ENGIE and Supply & Energy Management:

ENGIE, a global leader in low-carbon energy and services, relies on its Global Business Unit Supply & Energy Management (GBU S&EM) to provide reliable, sustainable, and affordable energy to all its customers. This strategic unit optimizes the Group’s and clients’ production assets and designs tailored energy solutions for our 200,000 professional clients and 15 million consumers.

The Global Business Unit Supply & Energy Management leverages ENGIE’s assets to deliver secure and sustainable energy to its B2B and B2C customers. It uses its expertise in energy management to provide decarbonized electricity 24/7.

Our Mission & Objectives

• Deliver carbon-free energy to clients around the world, 24/7


• Maximize the value of ENGIE’s diverse assets—including renewables, thermal generation, and storage


• Serve over 15 million residential customers and 200,000 businesses, aiming to reach 550 TWh by 2030 with a growing share of green electricity


• Promote agility, collaboration, and transparency throughout the organization

S&EM is structured around three core pillars:

• OneB2B: Focused on streamlining and scaling ENGIE’s business-to-business solutions across multiple countries


• OneB2C: Dedicated to business-to-consumer operations


• Energy Management: Overseeing the optimization and risk management of energy assets and portfolios

OneB2B – Strategic Focus. As a key pillar, OneB2B drives ENGIE’s B2B strategy by accelerating the delivery of tailored solutions, reducing operational costs, and leveraging unified platforms and shared tools. The team is committed to:

• Speeding up time-to-market for innovative B2B offerings


• Lowering service and build costs


• Developing the Bee-Stone suite—a unified platform that balances global standards with local needs


• Aligning IT and business strategies across geographies


• Implementing agile methodologies and strong governance to support long-term goals

Joining Supply & Energy Management means becoming part of a team of over 10,000 passionate experts spread across 20 countries, all united by a shared mission: shaping a greener and more efficient energy future. Together, we push the boundaries of innovation to deliver decarbonized energy 24/7. Join us and be part of those shaping the energy of tomorrow!

Context of the Supply Portfolio Management (SPM) – Strategic Importance

SPM plays a vital role in modeling and hedging energy risks for client portfolios. The function is evolving from locally fragmented teams to a more centralized, harmonized approach. Key transformation initiatives include:

• Establishing a central SPM entity to develop consistent methods and tools


• Building a collaborative, cross-geography SPM community


• Supporting career growth for portfolio managers


• Promoting best practices and unified risk representation


• Implementing scalable, automated systems for improved forecasting, pricing, and contract management

Our teams are committed to fostering a culture of collaboration, knowledge sharing, and continual improvement, ensuring both global alignment and local value creation for ENGIE’s clients and stakeholders.

Within SPM the transversal domain TrueWatts is in charge of:

• gathering people in charge of actuals consumption management


• sharing good practice


• build expertise on data modeling and grid error management


• design the MPD features and support its deployment (MDP is the product in charge of metering data management in Engie)

This domain is composed of several operational Middle Offices, in charge of certifying the actuals (balancing and billing volumes) for all Supply processes, leveraging the use of MDP.

Additionally, the core product team is the small data science team in charge of designing the core features that will be industrialized by MDP IT teams. The features support all the grid data imperfections: holes in timeseries, inconsistencies between sources, etc. From the detection of inconsistency patterns to the correction algorithm, this team is charge of settling the common framework use through all the B2B countries.

About the TrueWatts Team within SPM

The TrueWatts domain is a dynamic and cross-functional teams at the heart of Supply Portfolio Management (SPM), dedicated to delivering excellence in actual consumption management. Our mission is to bring together experts of dedicated Middle Offices to certify actual consumption volumes—balancing and billing—for every Supply process.

The TrueWatts domain plays a pivotal role in designing and deploying the MPD (Bee Stone metering data management product) for ENGIE. We support its implementation by developing innovative features and ensuring best practices are shared across all operational Middle Offices, making full use of MPD’s capabilities.

At the core of TrueWatts is a focused data science team that creates and refines the foundational algorithms powering the MPD curation pack. We tackle challenges such as gaps in time series data, inconsistencies between sources, and grid data imperfections. Our work ranges from detecting patterns of inconsistency to building correction algorithms, establishing a robust framework that is applied across all ENGIE’s B2B operations worldwide.

Joining TrueWatts means being part of an innovative and collaborative environment, where your contributions will directly drive the energy data reliability and help shape green and competitive offers. If you’re excited by solving complex data challenges and making a real impact on the energy sector, the TrueWatts domain is the place for you.

Role:

As senior data scientist in the core business team of the TrueWatts domain, you will:

• Identify and analyze patterns of inconsistencies across the various available data sources.


• Develop and implement algorithms to correct detected inconsistencies.


• Design and deploy operational quality monitoring dashboards for use by Middle Offices.


• Work daily to enable Middle Offices to effectively fulfill their responsibilities across different Supply processes, including forecasting, pricing, billing, closing, and customer care.


• Support the industrialization of data processing solutions developed by the business team in collaboration with IT teams.

Hard skills:

1. Data Platforms & Environment

• Expert command of Databricks (Spark, notebooks, Delta Lake) to design, build, and scale data workflows end-to-end.


• Deep understanding of cloud data environments (Azure or AWS) and modern data pipeline orchestration (Delta Live Tables, workflow automation).

2. Data Engineering & Quality Management

• Advanced proficiency in SQL and PySpark for large-scale data transformation, integration, and quality control.


• Proven experience designing robust inconsistency detection frameworks (validation layers, anomaly detection, quality metrics).


• Capability to develop and implement automated correction algorithms, from business rule definition to deployment in production.


• Solid knowledge of data quality governance, including testing, monitoring, and continuous improvement.

3. Data Science & Analytical Insight

• Strong skills in Python (pandas, scikit-learn, PySpark MLlib) for advanced analysis, pattern discovery, and model development.


• Ability to design analytical approaches to uncover hidden patterns, detect anomalies, and explain data discrepancies.


• Proven experience in timeseries management and statistics


• Track record of translating complex business challenges into actionable data models and measurable outcomes.

4. Industrialization & Delivery

• Experience deploying, scaling, and maintaining data science solutions in production environments.


• Familiarity with DevOps/MLOps practices (CI/CD, version control, testing, monitoring) to ensure reliability and reproducibility.


• Strong focus on documentation, traceability, and maintainability of solutions over time.


• Demonstrated expertise in managing Git repositories, including branching strategies, code reviews, and collaborative workflows, as well as maintaining comprehensive and up-to-date project documentation within Git platforms.

Soft skills:

Leadership, Initiative & Collaboration

• Proven ability to take initiative: propose new analytical approaches, identify opportunities for data quality improvement, and challenge existing processes.


• Comfortable collaborating with business and technical stakeholders, turning complex data insights into strategic recommendations.


• Capable of leading operational adoption of solutions, supporting users, and driving continuous enhancement of the data ecosystem.

Education and professional background:

• Engineering degree or business school, master


• 5 years' experience in similar role is required

Languages:

• English (Must) / French (is a plus) / Dutch (is a plus)

Travels:

The job is based in Zwolle or in Paris/Lyon, occasionally travels required to Paris/Lyon and in Europe

If you meet these requirements, then you are the talent we are looking for. Do not waste time!

Research shows that men already apply for a position when they meet around 60% of the requirements set by a prospective employer, while women tend to apply only when they feel they are a 100% match. What a shame! If you do not meet all the requirements but are interested in this role, please let us know. We would be happy to get in touch with you.

About ENGIE:

Our group is a global reference in low-carbon energy and services. Our purpose (“raison d’être”) is to act to accelerate the transition towards a carbon-neutral world, through reduced energy consumption and more environmentally-friendly solutions, reconciling economic performance with a positive impact on people and the planet. We rely on our key businesses (gas, renewable energy, services) to offer competitive solutions to our customers. With our 170,000 employees, our customers, partners and stakeholders, we are a community of Imaginative Builders, committed every day to more harmonious progress