Postdoctoral Fellow – AI/ML for Drug Metabolite Identification Full-time NEW

Postdoctoral Fellow In Machine Learning And Artificial Intelligence

As the world's leading pharmaceutical company, Pfizer is uniquely positioned with some of the largest and most complex chemical and biological data sets available anywhere. The Computational Absorption, Distribution, Metabolism, and Excretion (cADME) group at Pfizer is responsible for maximizing the value of ADME, Safety, and Pharmacology data generated to support drug discovery project teams. The Biotransformation group provides issue-driven drug metabolism expertise, including metabolite identification, structural elucidation, and interpretation of metabolic pathways, to support project teams across drug discovery and development.

We are seeking a highly motivated postdoctoral fellow with expertise in machine learning (ML) and artificial intelligence (AI) to develop predictive models for small-molecule drug metabolism. The role offers a unique opportunity to apply advanced ML/AI approaches to real-world pharmaceutical data at unprecedented scale, in close collaboration with experts in biotransformation, drug safety, and computational ADME. The fellow will have the opportunity to work with large-scale experimental metabolite identification (MetID) data, leveraging Pfizer's extensive, curated in vitro metabolism data assets to enable data-driven prediction of metabolic sites, metabolite structures, and transformation pathways.

This project aims to develop interpretable, mechanistically grounded ML models trained on empirical metabolite structure and abundance data and to integrate these predictive capabilities into AI-enabled decision-support workflows for drug discovery and development. This role will work closely with metabolism experts in real-time, testing and validating these models as experimental data is generated. The models developed in this project will be immediately impactful on internal decision making as well as influence the scientific field and regulatory landscape through external publication and application to ongoing evaluations.

Key Responsibilities

• Develop machine learning models to predict sites and types of small-molecule metabolism using large, curated MetID datasets.
• Perform data engineering to represent metabolic reactions, structural changes, and atom-level involvement in biotransformation for efficient use in predictive models.
• Train, evaluate, and interpret ML models using experimentally derived metabolite structure and abundance of data.
• Collaborate closely with biotransformation, drug safety, and computational ADME scientists to ensure scientific relevance.
• Contribute to integration of predictive metabolism models into AI- and LLM-enabled decision-support workflows.
• Communicate results through internal presentations, cross-functional discussions, and scientific publications.

Required Qualifications

• PhD in a relevant discipline such as computational chemistry, cheminformatics, machine learning, data science, or a closely related field.
• Strong background in machine learning and/or artificial intelligence applied to large, complex scientific datasets.
• Experience working with chemical structure data and molecular representations or an interest in learning.
• Demonstrated ability to develop predictive models using empirical, experimentally derived data.
• Programming experience sufficient for large-scale data engineering and ML model development.

Preferred Qualifications

• Ability to work effectively in a highly collaborative, interdisciplinary research environment.
• Strong written and verbal communication skills.
• Experience or familiarity with drug metabolism, biotransformation, MetID, or ADME-related data is advantageous.
• Interest in interpretable and mechanistically grounded ML approaches applied to drug discovery.

Additional Information

• Less than 2 years of post-degree experience.
• Willingness to make a minimum 2-year commitment.
• Successful record of scientific accomplishments evidenced by scientific publications and/or presentations with at least one first-author publication in a peer-reviewed journal.
• Two letters of recommendation are also required prior to interview stage.
• Relocation support available
• Work Location Assignment: Hybrid