Postdoctoral Fellow, AI for Quantitative Medicine Full-time NEW

Postdoctoral Fellow

At Pfizer, our purpose is to deliver breakthroughs that transform patients' lives. Central to this mission is our Research and Development team, which strives to convert advanced science and cutting-edge technologies into impactful therapies and vaccines. Whether you are engaged in discovery sciences, ensuring drug safety and efficacy, or supporting clinical trials, your role is crucial. You will leverage innovative design and process development capabilities to expedite the delivery of top-tier medicines to patients globally.

This Postdoctoral Fellow will lead innovative research at the intersection of artificial intelligence, medical imaging, pharmacometrics, and oncology drug development, with the goal of transforming how early treatment response is measured and used in clinical decision-making. This role will focus on developing and validating AI-powered quantitative imaging biomarkers that provide earlier, more sensitive, and more prognostic measures of treatment efficacy than current standards.

Working within a global R&D environment, the Fellow will leverage large-scale multimodal clinical trial datasets—integrating radiological imaging, pharmacokinetics/pharmacodynamics (PK/PD), and clinical outcomes—to advance next-generation early response endpoints. The work will potentially support early oncology drug development, dose selection, and trial design and materially accelerate portfolio decisions and improve probability of clinical success.

The role offers a unique opportunity to conduct impact-driven research with real-world translational application, collaborating closely with cross-functional partners across Oncology Development, Data Sciences & Analytics, and R&D AI innovation teams, as well as external AI and academic collaborators.

What You Will Achieve

• Scientific Leadership in AI-Enabled Biomarker Development Provide intellectual leadership in the development and validation of advanced AI models (e.g., deep learning–based imaging biomarkers) to quantify and predict tumor response from longitudinal clinical trial data.
• Integration of Multimodal Clinical Data Lead the integration of medical imaging, PK/PD, and clinical outcome data to establish mechanistic and predictive relationships between early response dynamics and downstream survival outcomes.
• Developing Novel Quantitative Modeling Approaches Explore development of modeling approaches (empirical, semi-mechanistic) that integrate AI enabled tumor response data to long term clinical outcomes
• Innovation in Early Response Endpoints Drive the conceptualization and evaluation of novel, continuous early response endpoints that address limitations of conventional criteria (e.g., RECIST), with a focus on clinical relevance and robustness.
• Translational Impact on Drug Development Decisions Translate methodological advances into scalable frameworks that can inform dose optimization, trial design, and early efficacy decision-making across oncology programs
• Cross-Functional and External Collaboration Collaborate effectively with internal stakeholders across Oncology Early- and Late-Stage Development, Data Sciences & Analytics, and AI innovation partners, as well as external technology and academic collaborators.
• Scientific Rigor and Reproducibility Ensure high standards of scientific rigor, validation, and documentation to support internal adoption, regulatory interactions, and broader reuse of developed methods and workflows.
• Knowledge Dissemination and Thought Leadership Communicate results through internal presentations, external scientific publications, and conference contributions, contributing to the organization's reputation as a leader in AI-enabled R&D.

Here Is What You Need (Minimum Requirements):

• PhD (or equivalent doctoral degree) completed by start date in a relevant field such as Biomedical Engineering, Chemical Engineering, Computational Biology, Biostatistics, Mathematics, Physics, Computer Sciences, Pharmaceutical Sciences or a related quantitative discipline.
• Demonstrated research experience applying machine learning or deep learning methods to biomedical, imaging, PK/PD, or clinical data.
• Proficient in at least one programing language (e.g., Python, R, MATLAB, etc.).
• Experience in machine learning/deep learning (PyTorch, TensorFlow), medical image analysis, and/or pharmacometrics.
• Strong foundation in deep learning methodologies (e.g., CNNs, Transformers, vision-language or multimodal models).
• Experience working with large, complex datasets and performing model development, validation, and performance evaluation.
• Ability to translate methodological innovation into practical, data-driven insights within a regulated or applied research environment.
• Strong written and verbal communication skills, with the ability to clearly explain complex technical concepts to interdisciplinary audiences.

Bonus Points If You Have (Preferred Requirements):

• Prior experience in oncology, medical imaging, or clinical trial PK/PD data analysis.
• Familiarity with tumor response assessment frameworks (e.g., RECIST) and their limitations in oncology.
• Experience integrating imaging data with clinical outcomes, PK/PD, or survival analysis.
• Track record of publications in high-impact journals or presentations at major scientific conferences.
• Experience collaborating with industry, translational research teams, or external technology partners.
• Interest in advancing AI methods with direct impact on drug development strategy and clinical decision-making.

Additional Information

• Relocation support available
• Work Location Assignment: Hybrid