Postdoctoral Fellow in AI/ML Applications for Vaccine Research & Development

Role Summary

Postdoctoral Fellow in AI/ML Applications for Vaccine Research & Development at Pfizer. The role focuses on developing advanced AI and machine learning approaches to accelerate pneumococcal vaccine development, collaborating with data science, preclinical, and clinical teams to translate findings into actionable insights.

Responsibilities

• Develop advanced AI and machine learning models, including transformer architectures and graph neural networks, to represent molecular features and predict immunogenicity of pneumococcal conjugate vaccines using preclinical and clinical data.
• Apply transfer learning to translate predictive models from preclinical to clinical domains and utilize interpretation frameworks (such as SHAP) to identify key molecular motifs for rational vaccine design.
• Conduct meta-analyses of large-scale immunogenicity datasets to characterize quantitative relationships between vaccine physical parameters and immunogenicity outcomes.
• Harmonize and curate preclinical and clinical datasets to support robust statistical and machine learning analyses.
• Engage in active collaboration with multidisciplinary teams, encompassing experts in data science, preclinical analysis, and clinical vaccine research, to advance pneumococcal conjugate vaccines development.
• Publish impactful scientific findings while safeguarding confidential data, ensuring clear, transparent reporting of methods and results to facilitate reproducibility and recognition in peer-reviewed journals and conferences.

Qualifications

• Required: Ph.D. in Computational Biology, Bioinformatics, Computer Science, Immunology, or a related field. Publication record with at least one first-author publication in a peer-reviewed journal.
• Required: No more than 2 years of post-degree experience.
• Required: Willingness to make a minimum 2-year commitment.
• Required: Demonstrated expertise in machine learning and deep learning, with hands-on experience in developing and validating predictive models for biological or biomedical data.
• Required: Proficiency in Python and AI/ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn). Experience with statistical modeling, including regression analysis and mixed-effects models.
• Required: Solid understanding of immunology, especially vaccine immunogenicity and conjugate vaccine design.
• Required: Strong data management and data curation skills, including harmonization of heterogeneous biological datasets.
• Required: Excellent scientific communication skills, with a track record of peer-reviewed publications or presentations. Ability to work across computational and wet-lab teams and distill complex results for diverse stakeholders.
• Preferred: Prior experience applying graph neural networks, transformer models, or cross-attention mechanisms to biological sequence or molecular structure data.
• Preferred: Familiarity with glycan-focused modeling and representation, including encoding of polysaccharide and protein carrier features.
• Preferred: Experience in translational research bridging preclinical and clinical datasets, especially in vaccine development.
• Preferred: Knowledge of SHAP or similar model interpretation frameworks for feature attribution in complex models.
• Preferred: Hands-on experience with ensemble modeling and transfer learning in biomedical contexts.
• Preferred: Collaborative experience with experimental biologists and vaccine R&D teams.
• Preferred: Familiarity with regulatory and translational aspects of vaccine development.

Skills

• Python programming
• PyTorch, TensorFlow, scikit-learn
• Machine learning and deep learning for biological data
• Statistical modeling (including regression and mixed-effects models)
• Immunology and vaccine design concepts
• Data curation and harmonization across heterogeneous datasets
• Scientific communication and cross-team collaboration

Additional Information

• Relocation support available
• Work Location Assignment: Hybrid