Senior Scientist I, Cheminformatics

Eikon Therapeutics•Millbrae, CA

7d•$178,000 - $215,250

About The Position

Eikon Therapeutics seeks a Senior Scientist with demonstrated success applying cheminformatics and machine-learning technologies to drug discovery programs. The role works closely with computational and medicinal chemists, software engineers, and machine-learning experts to turn assay and structure-activity data into interpretable information for decision-making. As part of the Drug Discovery team, the Senior Scientist will help accelerate discovery programs and contribute to developing treatments for patients. The role applies cheminformatics and data-mining methods to molecular modeling, virtual screening, and structure-activity relationship analysis. It includes processing chemical and biological datasets, evaluating drug-like and ADMET properties, using molecular fingerprints and descriptors, supporting AI/ML property-prediction models, and optimizing chemical-data pipelines. The scientist will collaborate across teams, maintain reproducible and well-documented analytical practices, guide library design and high-throughput screening analysis, assess SAR and compound properties, and work with medicinal chemists to triage emerging hits. Candidates must meet one of the stated education and experience combinations: a Ph.D. plus 5 years of relevant experience, a Master's degree plus 14 years, or a Bachelor's degree plus 16 years. The position calls for strong cheminformatics, machine-learning, ligand-based design, QSAR, programming, and drug-discovery experience, as well as effective communication and problem-solving skills.

Requirements

Ph.D. plus 5 years of relevant experience, or Master's degree plus 14 years of relevant experience, or Bachelor's degree plus 16 years of relevant experience.
Expertise in cheminformatics data analysis, data mining, and machine-learning models for drug-discovery problems.
Expertise in ligand-based design approaches, QSAR, and multiparameter optimization to rationalize SAR and design novel molecules.
Experience with scientific programming languages such as Python, RDKit and other cheminformatics libraries, and data-analytics tools such as Spotfire, DataWarrior, and D360.
Experience in virtual screening, HTS triaging, hit calling, and diversity analysis.
Familiarity with commercial platforms and ELN/registration systems such as Schrödinger, OpenEye, MOE, Dotmatics, DataBricks, and KNIME.
A track record of publications, patents, and/or conference presentations in computational chemistry and/or drug discovery.
Excellent problem-solving abilities and ability to work in a fast-paced, dynamic research environment.
Strong communication skills and ability to convey complex scientific concepts to technical and non-technical stakeholders.

Responsibilities

Develop and apply cheminformatics data-mining algorithms to analyze molecular modeling, virtual screening, and structure-activity relationships.
Process and analyze chemical and biological datasets to evaluate drug-likeness, ADMET properties, dosing, and related properties.
Use molecular fingerprints, descriptors, and similarity metrics for compound clustering, classification, and regression.
Assist in developing, maintaining, and monitoring AI/ML models for property prediction.
Optimize pipelines for processing and storing chemical structures using cheminformatics toolkits such as RDKit.
Collaborate with cross-functional teams to integrate computational approaches into curation and analysis workflows.
Maintain best practices for data integrity, reproducibility, and documentation of QSAR AI/ML models.
Guide the application of modern cheminformatics and ML/AI methods to library design, including diversity, focused, fragment, and DEL libraries, and analyze large HTS datasets to build predictive models.
Apply expert analysis of SAR, physicochemical properties, and ADMET properties.
Work with medicinal chemists to triage emerging hits from HTS.
Collaborate with the data science team to integrate AI/ML tools into chemistry and drug-discovery processes.