Sr Scientist, Quantitative Bioimaging

AbbVie•Worcester, MA

6d•$109,500 - $208,500•Onsite

About The Position

We are seeking a Senior Scientist to advance quantitative bioimaging capabilities in support of immunology discovery research. In this role, you will work within a cross-functional team with access to multiple microscopy modalities, complex in vitro models, multimodal biological datasets, and advanced computational infrastructure. You will develop and apply quantitative imaging, computer-vision, and machine-learning approaches to characterize cellular and tissue phenotypes, support the development of biological models, including co-cultures, organ-on-chip systems, organoids, and tissue explants, and generate insights that advance immunology discovery programs. This role combines hands-on delivery of robust, reproducible image-analysis workflows with the evaluation and application of advanced AI/ML approaches, including biomedical image segmentation, representation learning, foundation models, and scalable computational workflows. You will partner closely with wet-lab scientists, imaging specialists, computational scientists, and other subject-matter experts to translate biological questions into rigorous and impactful analysis strategies. The role sits at the intersection of biology, bioengineering, microscopy, and computational science. Candidates with combined expertise in two or more of these areas are especially encouraged to apply.

Requirements

BS, MS, or PhD in engineering, biophysics, computational biology, imaging science, bioinformatics, or a related discipline, with typically 10-12+ (BS), 8-10+ (MS), or 0-4+ (PhD) years experience.
Demonstrated experience developing quantitative image-analysis or computational solutions involving one or more of the following: image segmentation, feature extraction, phenotypic profiling, object classification, or analysis of high-content imaging data.
Experience with at least one relevant imaging modality or assay type, such as confocal microscopy, high-content imaging, or cell painting.
Ability to assess image quality, recognize common imaging artifacts, and interpret biologically meaningful phenotypes.
Working knowledge of machine-learning or deep-learning approaches for biological imaging, with the ability to understand model behavior, assess performance, and contribute to appropriate evaluation strategies.
Proficiency with the Python data-science ecosystem, including NumPy, pandas, Polars, scikit-learn, and/or PyTorch.
Strong biological grounding, attention to experimental rigor, and demonstrated ability to collaborate effectively with wet-lab and computational colleagues.
Excellent written, verbal, and presentation skills, including the ability to explain methods, results, assumptions, and limitations to diverse audiences.

Nice To Haves

Experience working with complex in vitro models, such as organoids, organ-on-chip systems, co-cultures, tissue explants, or other advanced in vitro platforms.
Experience with classical bioimage-analysis tools such as CellProfiler, scikit-image, ImageJ/Fiji, or comparable platforms.
Exposure to deep-learning, self-supervised learning, foundation-model, embedding-based, or multimodal AI approaches for biological imaging.
Peer-reviewed publications, patents, conference presentations, or other demonstrated scientific contributions in quantitative bioimaging, computer vision, computational biology, bioengineering, or a related field.

Responsibilities

Develop, optimize, and apply imaging assays and quantitative image-analysis workflows for 2D and 3D cellular and tissue models to characterize cellular and other complex biological phenotypes.
Collaborate with wet-lab assay scientists, imaging specialists, and computational scientists from experimental and assay design through image acquisition, analysis, validation, and data delivery.
Extract biologically meaningful, multiparametric features from high-content imaging datasets and use them to characterize disease-relevant phenotypes, mechanisms, and treatment responses.
Apply statistical, machine-learning, and deep-learning methods to identify candidate imaging biomarkers and relate imaging phenotypes to molecular, functional, and other biological readouts.
Contribute to the integration of imaging data with multimodal datasets, including molecular, single-cell, spatial, or perturbational data, where appropriate.
Establish quality-control and evaluation frameworks to assess image and assay quality, distinguish biological signal from technical artifacts, and define data-quality criteria, acceptance thresholds, and analytical limitations.
Maintain clear experimental and analytical records; analyze, visualize, and present results rigorously to both technical and nontechnical audiences.
Communicate methods, assumptions, results, uncertainties, and limitations effectively to cross-functional project teams.
Stay current with advances in quantitative bioimaging, image analysis, computer vision, and AI/ML for biological imaging, and evaluate opportunities to incorporate relevant approaches into team workflows.