Computational Chemometrics Researcher

Design, develop, and implement advanced chemometric and hybrid modeling frameworks for chemical and process systems, including statistical latent-variable-based methods, Bayesian statistical learning, physics- and chemically-informed machine learning approaches, spectral and chromatographic modeling, and uncertainty quantification. Define and guide methodological strategy by selecting appropriate modeling approaches to balance interpretability, robustness, and predictive performance in complex chemical environments. Collaborate closely with chemists, process engineers, and domain experts to translate physicochemical behavior, operating regimes, and sources of variability into structured analytical problems and computational solutions. Develop robust, scalable, and deployable models capable of handling noisy, sparse, and biased datasets, ensuring stability across varying operating conditions and enabling real-time or near-real-time application. Ensure model credibility through rigorous validation against experimental, simulated, and operational data, incorporating constraints and preserving interpretability. Apply chemometric and statistical methods to enhance process understanding by identifying drivers of variability, detecting anomalies, performing root-cause analysis, and supporting monitoring, control, optimization, and scale-up. Drive innovation in AI-enabled data analysis by exploring techniques such as deep learning for spectroscopy, manifold learning, probabilistic modeling, and physics-informed or chemistry-constraint-guided ML for chemical systems. Contribute to scientific leadership by publishing research and developing intellectual property to strengthen capabilities in digital chemistry and advanced analytics.