• Partner with stakeholders to turn business needs and scientific questions into data-driven strategy• Design, develop, and enhance ML models for catalyst performance prediction• Apply advanced analytics techniques, exploratory data analysis, feature engineering, model selection, hyperparameter tuning, and model performance assessment• Document model assumptions, methods, validation results, and recommendations in a reproducible way• Explore relevant databases and available data sources to understand data structures, completeness, quality, and usability for modelling• Unlock insights from correlations, patterns, outliers, and potential performance drivers within catalyst, emissions, laboratory, product, and process data• Develop scalable workflows that support efficient re-use of cleaned datasets• Work with catalyst, process, product, and laboratory data to identify performance drivers and relevant modelling features• Help advance the transition from exploratory analysis and prototype models to robust, usable modelling assets for the Project Team• Communicate insights and recommendations in a clear, compelling way that inspires action across technical and non-technical stakeholders

You'll stand out with these Skills:

Technical - mandatory

• • Master's degree in Data Science/Statistics/Mathematics/Computer Science/Engineering/Physics, Chemistry/Materials Science or a related discipline• Around 5 years of expertise in data science, machine learning, statistical modelling, or predictive analytics• Solid Python programming skills and hands-on experience with pandas, NumPy, scikit-learn, matplotlib• Proven expertise with database exploration, data cleaning/preparation, exploratory data analysis, and correlation analysis• Experience in developing and improving predictive models using complex technical or scientific datasets, in working with structured data from industrial, engineering, manufacturing, laboratory, or R&D environments• Ability to translate analytical findings into clear visualizations, technical documentation, and model interpretation