Principal Chemist

Ecolab•Eagan, MN

About The Position

The Principal Chemist on the RD&E AI Technologies team executes key elements of the RD&E AI strategy by developing and applying computational chemistry, molecular modeling, and data-driven methods to RD&E problems. This role partners with chemists, engineers, and digital/data teams to translate high-impact RD&E questions into fit-for-purpose models, workflows, and decision-support tools that accelerate innovation and improve operational efficiency. The role also contributes to building sustainable, AI-ready scientific data foundations and promotes responsible AI practices across RD&E. A trusted partner at nearly three million customer locations, Ecolab (NYSE:ECL) is a global sustainability leader offering water, hygiene and infection prevention solutions and services that protect people and the resources vital to life. Building on a century of innovation, with an annual sales of $15 billion and more than 48,000 associates, Ecolab delivers comprehensive science-based solutions, data-driven insights and world-class service to advance food safety, maintain clean and safe environments, and optimize water and energy use, and improve operational efficiencies and sustainability for customers in the food, healthcare, life sciences, hospitality and industrial markets in more than 170 countries around the world. When you come to work at Ecolab, you get to take on some of the world’s most meaningful challenges and have the opportunity to learn and grow, shape your career, make an impact and quickly see the importance of your work.

Requirements

MS Computational Chemistry or Chemistry and 3 years of related experience or PhD in Computational Chemistry or Chemistry (with computational focus).
Hands-on experience applying computational methods to chemical/materials problems.
Programming proficiency in Python.
Experience with scientific computing workflows, version control, and reproducible analysis practices.
Working knowledge of cheminformatics and molecular representations (e.g., fingerprints/descriptors, SMILES, graph-based representations) and familiarity with common chemistry toolkits (e.g., RDKit or equivalent).
Ability to translate scientific questions into modellable problems and to communicate results, uncertainty, and tradeoffs clearly to diverse stakeholders.
Demonstrated collaboration skills in cross-functional environments
No immigration sponsorship available for this role

Nice To Haves

Experience with quantum chemistry and/or molecular simulation software (commercial or open-source) and associated workflows (e.g., structure preparation, conformer generation, parameterization, job orchestration, post-processing).
Experience developing ML models for chemical/property prediction (QSPR/QSAR) and familiarity with evaluation approaches for small/medium scientific datasets.
Familiarity with GenAI/LLM applications in scientific contexts and an understanding of risks and controls.
Exposure to cloud or enterprise analytics platforms (e.g., Azure, Databricks) and collaborating with data engineering partners on pipelines, access, and security/compliance.
Demonstrated scientific communication (e.g., peer-reviewed publications, conference presentations, internal technical reports) and ability to produce clear technical documentation.

Responsibilities

Execute on the RD&E AI playbook by delivering computational chemistry and AI-enabled capabilities that measurably accelerate RD&E innovation and operational efficiency.
Develop, run, and interpret computational chemistry and molecular modeling approaches appropriate to the business question (e.g., quantum chemistry/DFT, molecular mechanics, MD, QSPR/QSAR, cheminformatics descriptors and featurization, surrogate modeling).
Build data pipelines and reusable analysis to curate, clean, and structure chemical and experimental data to enable AI-ready datasets and reproducible modeling.
Create and evaluate predictive and/or generative models for chemistry-relevant tasks (e.g., property prediction, similarity search, molecular representation learning).
Document methods, datasets, assumptions, limitations, and results clearly to communicate with both technical and non-technical audiences.
Support responsible AI by applying appropriate model evaluation, bias/error analysis (as relevant), traceability, and governance-aligned documentation.
Contribute to RD&E AI readiness by sharing best practices and participating in workshops/demos that help scientists adopt AI tools effectively.