Postdoctoral Fellow, AI/ML & Computational Immunology

Pfizer • Cambridge, MA

1d • $64,600 - $107,600 • Hybrid

About The Position

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. What You Will Achieve The Systems Immunology group within the Inflammation and Immunology Research Unit at Cambridge, MA is seeking a highly motivated Ph.D.-level computational scientist to join as a Postdoctoral Research Fellow. This role will advance therapeutic innovation through the development and deployment of next-generation AI/ML toolkits to decode macrophage biology, efferocytosis, and myeloid cell states in inflammation and fibrotic disease pathophysiology. Systems immunology at Pfizer leverages high-dimensional omics data—including single-cell and spatial transcriptomics, multi-omics integration, and advanced computational platforms—to understand immune dysfunction and therapeutic mechanisms in human disease. Our team generates and analyzes clinical and translational datasets to inform target and indication selection, patient stratification, biomarker discovery, and combination therapies, bridging experimental biology with computational innovation. Complementing our experimental inflammation and fibrosis research, this computational postdoc will work at the interface of AI/ML, systems immunology, and myeloid biology to accelerate the discovery of first- and best-in-class therapeutics. The postdoctoral research project aims to develop a computational framework to deconvolve efferocytosis events—the clearance of apoptotic cells by macrophages—from single-cell and spatial omics data. Efferocytosis is critical for tissue homeostasis and immune balance, yet its transcriptional signatures are obscured in current scRNA-seq analyses, where mixed host-cargo transcriptomes are discarded as technical artifacts. This project will build and validate deep learning models to recover efferocytic events, predict macrophage phenotypic transitions, and nominate therapeutic targets using interpretable machine learning. The framework will be deployed across Pfizer's internal datasets and public resources to link macrophage-cargo interactions to disease outcomes in fibrosis, inflammation, and neurodegeneration. The ideal candidate should have strong computational and quantitative training with domain interest or expertise in immunology, inflammation, and/or systems biology. The Postdoctoral Fellow will gain deep expertise in AI/ML for single-cell omics, work collaboratively across Pfizer's multidisciplinary systems immunology and discovery biology teams, and contribute to high-impact publications. By the end of the program, the postdoctoral fellow will be skilled in computational model development, biological interpretation of complex datasets, and effective science communication.

Requirements

• A Ph.D. (or thesis defense within 2-3 months) in computational biology, bioinformatics, computer science, statistics, biomedical engineering, immunology with strong quantitative focus, or a related field.
• Willingness to make a minimum 2-year commitment.
• Less than 2 years post-doctoral experience.
• Provide two letters of recommendation.
• At least 1 first-author scientific research article in high-quality specialty or general readership journals.
• Experience analyzing single-cell RNA-seq data; familiarity with common preprocessing, QC, integration, and annotation approaches.
• Proficiency in at least one scientific programming language (Python and/or R) and ability to write maintainable, well-tested code.
• Experience with machine learning methods (e.g., representation learning, deep learning, classification/regression) and model evaluation/benchmarking.
• Ability to work with large datasets and modern compute environments (HPC and/or cloud), including reproducible workflow practices.
• Strong scientific communication skills (writing and presentations) and the ability to collaborate effectively across disciplines.
• Excellent organizational skills, self-motivated, team-oriented, ability to multitask with attention to detail.
• Ability to work collaboratively in a team environment.

Nice To Haves

• Experience with spatial transcriptomics/omics (e.g., Visium, VisiumHD, Xenium, Slide-seq) and spatial analysis frameworks.
• Experience with deep learning architectures relevant to omics (e.g., transformers, VAEs, graph neural networks) and/or multi-task learning.
• Familiarity with interpretability techniques (e.g., feature attribution, perturbation/what-if analyses) and/or causal inference concepts for biological discovery.
• Domain knowledge of inflammation and fibrosis biology.
• Experience integrating multi-modal datasets (e.g., RNA+ATAC multiome, protein, imaging) and building reusable toolkits.
• Comfort using modern AI assistants (e.g., Claude/Microsoft Copilot) to accelerate coding, documentation, and problem solving—paired with strong scientific judgment and validation.
• Proficiency in -omic data analysis software and tools (e.g., Seurat, Scanpy, Squidpy, pathway enrichment, network analysis).
• In-depth, hands-on knowledge of inflammation and fibrosis biology.
• Experience or familiarity with wet-lab protocols for generating high-dimensional sc/nRNA-Seq data (e.g., 10X Genomics library preparation, Smart-Seq2-4 plate-based protocols, etc.)

Responsibilities

• Design and build machine learning models to detect, deconvolve, and interpret efferocytosis events from scRNA-seq and spatial omics data (e.g., recovering mixed host/cargo transcriptomes).
• Generate and curate training/validation datasets (including cross-species and multi-omic settings), as well as establish robust benchmarking and quality metrics.
• Develop end-to-end analysis toolkit/pipeline (data ingestion, model training, inference, interpretability, and reporting) with reproducible workflows.
• Integrate model outputs with downstream biological questions—linking efferocytosis to macrophage state transitions, pathway activation, and disease-associated phenotypes.
• Apply interpretable machine learning approaches to nominate and prioritize therapeutic targets and hypotheses for experimental follow-up.
• Collaborate closely with wet-lab and translational partners (myeloid biology, fibrosis, spatial omics teams) to refine biological questions, validate findings, and iterate on models.
• Independently interpret and analyze data to communicate findings to mentors and collaborators, making decisions using technical and biological knowledge under supervision.
• Communicate results through internal presentations, external conferences, and manuscripts for peer-reviewed publication.
• Ensure all tasks and responsibilities are carried out according to scientific and ethical standards.
• Build team skills and a culture of scientific excellence and continuous learning.

Benefits

• We offer comprehensive and generous benefits and programs to help our colleagues lead healthy lives and to support each of life’s moments. Benefits offered include a 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, and health benefits to include medical, prescription drug, dental and vision coverage.

What This Job Offers

• Job Type: Full-time
• Education Level: Ph.D. or professional degree