Aerodynamic AI Engineer

The Aerodynamic AI Engineer is part of a dedicated team leveraging data and artificial intelligence to enhance aerodynamic development, performance analysis, and operational efficiency within the Aerodynamics department. Reporting to the Lead AI Engineer, you will work on specialist projects that bridge aerodynamic engineering and AI — developing advanced machine learning models, surrogate models, and automated geometry tools that give Williams Racing a competitive edge in vehicle development.

This is a technically demanding, hands‑on role in a fast‑paced, high‑pressure environment. You will collaborate closely with aerodynamicists and CFD engineers, translating complex engineering requirements into practical AI solutions and communicating your findings with clarity and impact.

• Develop and deploy AI models for the analysis of CFD simulation data, extracting insights to support aerodynamic development decisions.
• Build advanced surrogate models for aerodynamic predictions, with a particular focus on fluid dynamics applications.
• Develop AI-driven mesh generation algorithms and automated geometry creation tools for aerodynamic applications.
• Conduct comprehensive analysis of wind tunnel data, including drift detection, anomaly identification, and statistical analysis to ensure data quality and reliability.
• Build and maintain robust CI/CD pipelines for AI model deployment, ensuring high code quality standards across all aerodynamic AI applications.
• Collaborate with aerodynamicists and CFD engineers to translate engineering requirements into AI solutions and communicate complex insights effectively.
• Stay current with emerging AI technologies relevant to computational fluid dynamics and aerodynamic applications.
• Identify AI-driven opportunities to improve aerodynamic development efficiency within cost cap requirements.

• Proven experience developing and deploying AI/ML models, particularly for scientific or engineering applications.
• Strong proficiency in Python with the PyTorch framework.
• Understanding of computational geometry principles and familiarity with mesh generation algorithms.
• Experience with statistical analysis and anomaly detection techniques for large scientific datasets.
• Strong software engineering practices including CI/CD pipeline development and code quality standards.
• Excellent communication skills, with the ability to collaborate across technical disciplines and translate complex AI concepts for engineering audiences.
• Demonstrated ability to manage multiple projects and deliver results in a fast‑paced, high‑pressure environment.
• Master's or PhD in Engineering, Physics, Computer Science, Mathematics, or a related scientific discipline (or equivalent practical experience).
• Experience with NVIDIA Physics Nemo or similar physics-informed machine learning frameworks.
• Knowledge of fluid dynamics concepts and CFD data analysis.
• Experience in motor sport, Formula 1, or aerospace aerodynamics.