Hybrid (can be based in wilmington, de, florence, ky, auburn hills, mi, or irving, tx)
Ai + physics-based machine learning
Predictive modeling for material properties
Bayesian optimization and experimental design
Celanese is seeking a Digital Innovation Engineer with expertise in predictive modeling and advanced experimentation, focusing on AI and physics applications to enhance product and material development. The position supports technology and innovation programs through quantitative methods and practical insights
Job Summary
This role applies rigorous quantitative methods including AI and physics to enable faster, more confident decisions in new product development.
The position involves designing advanced experimental strategies and Bayesian optimization to efficiently explore high-dimensional design spaces.
Candidates will translate complex modeling outputs into actionable insights to support technology and innovation programs across the organization.
Matching Summary
Match Score: 85
Celanese is seeking a Digital Innovation Engineer with expertise in predictive modeling and advanced experimentation, focusing on AI and physics applications to enhance product and material development. The position supports technology and innovation programs through quantitative methods and practical insights.
Skills & Requirements
Must-have
AI + physics-based machine learning
Predictive modeling for material properties
Bayesian optimization and experimental design
Uncertainty quantification and model validation
Applied statistics and probabilistic modeling
Nice-to-have
Understanding of advanced materials and chemical processes
Experience with full-stack application development
Strong communication skills for technical stakeholders
Cross-functional collaboration in innovation teams
Key Requirements
Master's Degree or higher in CS, Physics, Math, or related field
1+ years experience in modeling development and data analysis
Proficiency in AI + physics-based machine learning approaches