Lead Data Scientist

Job Description SummaryGE Vernova is accelerating the path to more reliable, affordable, and sustainable energy, while helping our customers power economies and deliver the electricity that is vital to health, safety, security, and improved quality of life. Are you excited at the opportunity to electrify and decarbonize the world?
We are looking for a passionate, creative, and results-driven Data Scientist with solid experience in developing and validating AI/ML models, typically gained through at least 5 years working within the energy sector or related domains such as smart infrastructure or industrial automation. The ideal candidate has a strong track record of independently leading and delivering AI/ML model projects in complex, data-rich environments, requiring someone who can drive innovation from concept to production.
As part of the Grid Automation organization, you will be at the forefront of developing, testing, and validating cutting-edge AI/ML models specifically designed for grid innovation applications. You will play a key role in designing and building robust validation frameworks that ensure AI/ML solutions meet stringent accuracy, performance, and operational standards across both edge and cloud environments.

Job Description

Essential Responsibilities:

• Design and conduct experiments to develop, test and validate AI/ML models in the context of energy systems and grid automation applications (including model selection, design, tuning, testing, refining, validation, optimization and deployment).
• Establish clear validation frameworks to ensure models meet required performance standards and business objectives.
• Establish test procedures to validate models with real and simulated grid data.
• Identify and address discrepancies between expected and actual model behavior, providing actionable insights to improve model performance.
• Implement automated testing strategies and pipelines to streamline model validation processes.
• Responsible for exploratory data analysis (EDA), reporting and visualization of results.
• Lead project stakeholder workshops to shape scope, designs and outcomes to ensure project vision becomes reality.
• Collaborate with Application Architects, Data Engineers, ML Engineers and MLOps Engineers to improve data quality, enhance model performance, and ensure efficient deployment of validated models.
• Ensure data adheres to data governance policies and industry standards.
• Communicate validation results, insights, and recommendations clearly to stakeholders, including product managers and leadership teams.
• Build necessary understanding and expertise to design and develop product features and applications such as Protection, Control, Monitoring and Communication

Must-Have Requirements

• PhD, Master’s, or Bachelor’s degree in Data Science, Computer Science, Electrical Engineering, or a related field with hands-on experience in model development and validation.
• Proven experience in the energy, smart infrastructure, or industrial automation sectors, with deep expertise in system protection, automation, monitoring, and diagnostics, typically acquired through a minimum of 5 years within a multinational manufacturing company.
• Substantial experience in building and validating AI/ML models, ensuring they meet business and technical requirements.
• Strong knowledge of statistical techniques, model technologies, performance metrics, and validation methodologies for AI/ML models.
• Proficiency in programming languages such as Python, R, or MATLAB.
• Experience with data wrangling, feature engineering, and preparing datasets for model development.
• Familiarity with machine learning frameworks (e.g., TensorFlow, PyTorch, Scikit-learn) and model evaluation techniques.
• Experience in exploratory data analysis (EDA), delivering actionable insights from data and data storytelling.
• Experience with cloud platforms (e.g., AWS, Azure, GCP) and deployment of models in cloud environments.
• Proficiency with data visualization tools and libraries such as Tableau, Power BI, or similar (matplotlib, bokeh, seaborn) to effectively present results and insights.

Nice-to-Have Requirements:

• Familiarity with big data tools and technologies, such as Hadoop, Kafka, and Spark.
• Familiarity with data governance frameworks and validation standards in the energy sector.
• Knowledge of distributed computing environments and model deployment at scale.
• Strong communication skills, with the ability to clearly explain complex validation results to non-technical stakeholders.

Additional Information