About the position
Pfizer's purpose is to deliver breakthroughs that change patients' lives. Research and Development is at the heart of fulfilling Pfizer's purpose as we work to translate advanced science and technologies into the therapies and vaccines that matter most. Whether you are in the discovery sciences, ensuring drug safety and efficacy or supporting clinical trials, you will apply cutting edge design and process development capabilities to accelerate and bring the best in class medicines to patients around the world. As a Cheminformatics Data Scientist, you will leverage data-driven approaches to tackle drug discovery chemical and biological challenges. You will apply and develop machine learning models for molecular property prediction, analyze and optimize hit-to-lead and lead optimization strategies from our proprietary knowledge base, and collaborate closely with both internal and external partners to maximize the value of our industry-leading datasets.
Responsibilities
- Develop and apply cheminformatics data-mining algorithms for the analysis of molecular modeling, virtual screening, and structure-activity relationship (SAR) analysis.
- Process and analyze chemical and biological datasets to evaluate properties such as drug-likeness, ADMET properties, dosing, etc.
- Utilize molecular fingerprints, descriptors, and similarity metrics for compound clustering, classification, and regression.
- Assist in development, maintenance, and monitoring of AI/ML models used for property prediction.
- Optimize data pipelines for processing and storing chemical structures using cheminformatics toolkits (RDKit, OpenEye, etc.).
- Collaborate with cross-functional teams to integrate computational approaches into curation and analysis workflows.
- Maintain best practices in data integrity, reproducibility, and documentation of QSAR AI/ML models.
Requirements
- Ph.D. with 0 years of experience or Master's degree with 2+ years of experience in Cheminformatics, Computational Chemistry, Bioinformatics, Data Science, or a related field.
- Proficiency in Python, with experience in cheminformatics libraries and topics (RDKit, OpenEye, DeepChem, InChI, SMILES/SMARTS).
- Experience working in a structured collaborative data and software development environment (git).
- Experience using SAR model-building software such as SciKit-Learn, Torch, etc.
- Strong understanding of basic statistical concepts and how to evaluate and track model performance.
Nice-to-haves
- Experience using DAGs to define data pipelines, e.g. Luigi, Airflow, Dagster, Prefect, Kubeflow.
- Experience working with relational (SQL) and NoSQL databases for chemical data management.
- Experience working with MLOps tools such as MLFlow, Neptune, or SageMaker.
Benefits
- 401(k) plan with Pfizer Matching Contributions and an additional Pfizer Retirement Savings Contribution.
- Paid vacation, holiday and personal days.
- Paid caregiver/parental and medical leave.
- Health benefits to include medical, prescription drug, dental and vision coverage.
