ROLE SUMMARY
As a Principal ML/AI Cheminformatics Data Scientist within the Computational Absorption, Distribution, Metabolism, and Excretion (cADME) group in Pfizer’s Pharmacokinetics, Dynamics, and Metabolism (PDM) organization, you will apply data-driven approaches to address critical challenges in small-molecule drug discovery.
In this role, you will develop, deploy, and continuously improve machine learning models for molecular property prediction and leverage Pfizer’s proprietary chemical and biological datasets to inform decision-making across hit-to-lead and lead optimization stages. Your work will directly enable more efficient compound prioritization, improved prediction of ADME properties, and accelerated progression of discovery programs.
Success in this position will be defined by the delivery of robust, validated computational models and workflows that generate actionable insights and measurable impact on project outcomes. You will collaborate closely with cross-functional PDM partners and external collaborators to integrate AI-driven approaches into discovery workflows and maximize the value of Pfizer’s industry-leading data assets.
ROLE RESPONSIBILITIES
- Drive scientific and technical advancement in PDM’s AI and cheminformatics capabilities by developing and delivering robust, validated workflows and algorithms that directly support drug discovery. Success will be measured by the implementation of effective AI-driven solutions, demonstrated impact on project outcomes, and the publication or presentation of results.
- Design, build, and deploy innovative cheminformatics and AI workflows for small molecule discovery, with clear deliverables including prioritized compound lists, well-defined chemical libraries, and actionable structure-activity relationship analyses.
- Collaborate closely with medicinal chemists, biologists, and data scientists to integrate computational approaches into experimental and analytical workflows. Success in this area will be reflected by joint project milestones achieved, co-authored publications, and the creation of interdisciplinary solutions that accelerate drug discovery.
- Continuously monitor and evaluate emerging advances in AI, cheminformatics, and computational drug discovery, proactively leading the adoption of promising new methodologies. Contributions will include piloting novel techniques, leading internal workshops or training sessions, and helping set strategic directions for technology adoption.
- Collaborate with cross-functional teams—including medicinal chemists, biologists, and data scientists—to integrate computational solutions into drug discovery workflows.
- Develop novel algorithms and analytical strategies tailored to Pfizer’s proprietary datasets and key scientific questions, with measurable outcomes such as validated models, software tools, and contributions to scientific literature or patent filings.
MINIMUM QUALIFICATIONS
- PhD in Cheminformatics, Computational Chemistry, Bioinformatics, Data Science, or a closely related field and a minimum of 4 years of relevant drug discovery experience in a pharmaceutical or biotech environment **OR**
- Master’s degree in Cheminformatics, Computational Chemistry, Bioinformatics, Data Science, or a closely related field and a minimum of 9 years of relevant drug discovery experience in a pharmaceutical or biotech environment
- Experience applying AI methods to medicinal chemistry or cheminformatics challenges, including work with molecular representations, chemical fingerprints, generative models, transformer architectures, pretraining strategies, property prediction, virtual screening, and ADMET modeling.
- Strong proficiency in Python, with hands-on experience using cheminformatics libraries and tools such as RDKit, OpenEye, DeepChem, InChI, and SMILES/SMARTS.
- Proven track record of creatively applying computational techniques to address problems relevant to pharmaceutical research and development.
- Experience communicating effectively and collaborating with diverse teams
- Experience delivering results in a fast-paced environment while managing multiple priorities.
