Back to search

Chemille Intern

Internship – AI-Assisted Chemical Resistance Prediction, supporting the development of advanced digital engineering tools for material selection within Chemille, Celanese's digital materials platform.

  • Meyrin, Geneva, Switzerland
  • Internship
  • Posted Nov 19, 2024
INDUSTRYSoftware & InternetSaaS & Enterprise Software

Responsibilities

  • Conduct literature reviews on chemical resistance, polymer degradation mechanisms, and materials informatics methodologies
  • Analyze existing chemical resistance data, testing reports, and technical documentation
  • Identify material, chemical, and environmental variables that influence chemical resistance performance
  • Evaluate and compare predictive modeling approaches, including knowledge-based systems, statistical models, machine learning algorithms, and AI methodologies
  • Develop datasets and data-processing workflows to support model development and validation
  • Design and execute laboratory validation testing to generate data required for predictive model development
  • Develop prototype predictive models using historical laboratory data and newly generated test results
  • Analyze model performance and compare predictions against experimental results, published literature, and expert assessments

Requirements

  • Master's degree in Materials Science
  • Master's degree in Chemistry
  • Master's degree in Chemical Engineering
  • Master's degree in Mechanical Engineering
  • Master's degree in Computer Science
  • Master's degree in a related STEM field
  • Experience in a Materials Science

Nice to have: Materials informatics, Predictive modeling

Skills

Artificial IntelligenceMachine LearningData analyticsDigital engineering toolsPolymer materials knowledgeMaterial characterizationChemical degradation assessmentData collection and analysisStatistical analysisMachine learning conceptsPythonJupyter NotebookPythonJupyter Notebook

Full description

Overview Internship – AI-Assisted Chemical Resistance Prediction Chemille is Celanese's digital material selection platform, providing customers with access to material properties, regulatory information, sustainability data, and technical documentation. Today, Chemille relies primarily on chemical resistance information derived from generic product line data and expert assessments. While this information provides valuable guidance, it does not fully capture the complex interactions between specific polymers, chemicals, concentrations, temperatures and exposure times. Recent advances in Artificial Intelligence (AI), Machine Learning (ML), and materials informatics offer the opportunity to develop predictive models capable of estimating chemical resistance behavior based on material characteristics and testing data. Such capabilities could significantly enhance material selection decisions and support customers during application development. Responsibilities The intern will gain hands-on experience supporting the development of advanced digital engineering tools for material selection within Chemille, Celanese's digital materials platform. This internship combines material science, laboratory testing, data analytics, and artificial intelligence to develop predictive models for chemical resistance of thermoplastics. The intern will work with engineers and digital innovation teams to investigate how AI and machine learning can enhance chemical resistance predictions and support future integration into Chemille. Depending on project needs, responsibilities may include: Conduct literature reviews on chemical resistance, polymer degradation mechanisms, and materials informatics methodologies Analyze existing chemical resistance data, testing reports, and technical documentation Identify material, chemical, and environmental variables that influence chemical resistance performance Evaluate and compare predictive modeling approaches, including knowledge-based systems, statistical models, machine learning algorithms, and AI methodologies Develop datasets and data-processing workflows to support model development and validation Design and execute laboratory validation testing to generate data required for predictive model development Develop prototype predictive models using historical laboratory data and newly generated test results Analyze model performance and compare predictions against experimental results, published literature, and expert assessments Qualifications Currently pursuing a Master's degree in Materials Science, Chemistry, Chemical Engineering, Mechanical Engineering, Computer Science, or a related STEM field Strong interest in Artificial Intelligence, Machine Learning, data analytics, and digital engineering tools Knowledge of polymer materials, material characterization, chemical degradation, or durability assessment through coursework, research, or previous internships Ability to collect, organize, analyze, and interpret technical and experimental data Familiarity with statistical analysis, data science, or machine learning concepts Experience with programming or data analysis tools such as Python, Jupyter Notebook Strong analytical and problem-solving skills with the ability to work on multidisciplinary technical challenges Effective written and verbal communication skills, including technical report writing and presentation development Experience or coursework related to machine learning, materials informatics, predictive modeling, statistics, or artificial intelligence is considered a strong advantage

Chemille Intern at Celanese | Referso Jobs