Senior Scientist II; Computational Chemistry

Position: Senior Scientist II (Computational Chemistry)
SUMMARY:

We are seeking a Senior Scientist II in Computational Chemistry to join our small-molecule discovery organization. The successful candidate will apply physics-based molecular modeling, cheminformatics, and data-driven methods to advance drug discovery programs. This role is designed for a scientist with a strong foundation in computational chemistry and a particular interest in connecting molecular simulation with cheminformatics, workflow automation, and practical machine learning.

The individual will contribute to molecular dynamics, free-energy calculations, structure-based design, and compound prioritization while developing reliable computational and machine learning workflows that increase the impact of predictive methods across discovery portfolio. Strong scientific judgment, programming ability, communication, and collaboration skills are essential. The successful candidate will work closely with medicinal chemists, structural biologists, biologists, pharmacologists, and bioinformatics scientists in a fast-paced, interdisciplinary research environment.

ESSENTIAL DUTIES AND RESPONSIBILITIES:

Apply ligand- and structure-based computational methods to support small-molecule discovery programs.

Plan, execute, analyze, and communicate molecular dynamics simulations and free-energy calculations for compound prioritization and molecular design.

Apply molecular docking, protein-ligand interaction analysis, conformational analysis, similarity searching, and other computational approaches to generate experimentally testable design hypotheses.

Use cheminformatics methods to analyze compound collections, explore structure-activity relationships, assess chemical diversity, and support virtual library design and prioritization.

Evaluate and apply appropriate machine-learning methods for molecular property or activity prediction, in combination with physics-based modeling and experimental data.

Assess machine-learning model performance and applicability using scientifically appropriate validation methods, and clearly communicate limitations and uncertainty. Apply and develop cheminformatics and machine learning models to enable predictive analytics across the pipeline

Contribute to virtual screening campaigns using structure-based, ligand-based, and fragment-based approaches.

Integrate computational results into collaborative discovery platforms and project workflows, including tools such as Live Design and Spotfire.

Collaborate closely with medicinal chemists, structural biologists, biologists, pharmacologists, and other project stakeholders to interpret data and influence compound-design decisions.

Present computational analyses, recommendations, assumptions, and uncertainties clearly to scientific project teams.

Stay current with emerging methods in molecular simulation, free-energy calculations, cheminformatics, machine learning, and computer-aided drug design.

Contribute to the continued development of computational chemistry capabilities and a predict-first culture within the discovery organization.

EDUCATION & EXPERIENCE:

Bachelor’s degree in related discipline and a minimum of 9 years of relevant experience; or,Master’s degree in related discipline and a minimum of 7 years of relevant experience; or,PhD in Computational Chemistry, Cheminformatics or related discipline, with at least 2 years of relevant experience in the biotechnology or pharmaceutical industry; or,Equivalent combination of education and experience.

KNOWLEDGE &

SKILLS:

Strong foundation in molecular modeling and the physical principles governing protein-ligand interactions. Hands-on experience with one or more structure-based drug-design methods, such as molecular docking, molecular dynamics, free-energy calculations, conformational analysis, or protein-ligand interaction analysis.

Proficiency in Python for scientific computing, data analysis, or computational workflow development.

Working knowledge of cheminformatics concepts, such as molecular representations, fingerprints, molecular descriptors, similarity searching, substructure searching, clustering, or compound-library analysis.

Familiarity with open-source cheminformatics or molecular-modeling tools, such as RDKit, OpenMM, GROMACS, AMBER, or comparable platforms.

Ability to analyze computational and experimental data critically and translate results into clear, testable molecular-design hypotheses. Understanding of structure-activity relationships and the physicochemical characteristics relevant to…