Senior Scientist, Informatics II Full-time NEW

AbbVie Immunology Discovery Pathology Group

The AbbVie Immunology Discovery Pathology group is at the forefront of AI-driven digital pathology, developing quantitative and translational pathology approaches to support target validation, deepen our understanding of disease biology, and advance drug discovery.

We are seeking an experienced and innovative Image Analysis Scientist with expertise spanning digital pathology, computer vision, machine learning, and scientific programming, combined with a strong foundation in immunology and tissue biology.

Our group generates quantitative insights from H&E and immunolabeled tissue sections and applies emerging spatial transcriptomics and high-plex spatial proteomics technologies to investigate cellular phenotypes, tissue organization, and spatial relationships within the tissue microenvironment.

The successful candidate will independently lead the development and application of advanced computer vision and machine-learning approaches for histopathology image analysis, including deep learning and representation learning. The candidate will also develop robust computational workflows for high-dimensional image-based spatial protein datasets, including approaches to identify and quantify cell populations, characterize cellular phenotypes, and analyze spatial relationships and tissue organization.

This individual will be part of a highly collaborative, multidisciplinary team and will work closely with pathologists, computational biologists, immunologists, and discovery scientists across the organization. The successful candidate will combine computational innovation with biological insight to develop and apply digital pathology approaches that address important scientific questions and help drive innovative drug discovery research.

Responsibilities

• Independently design, develop, optimize, and validate advanced machine learning, deep learning, and computer vision approaches for digital pathology, including cell and tissue segmentation, classification, feature extraction, and representation learning, to identify and quantify histopathologic features, cellular phenotypes, and spatial relationships.
• Develop and deploy robust image analysis workflows for high-dimensional, multiplexed imaging datasets to quantify cell populations and phenotypes and characterize spatial relationships and tissue organization.
• Apply appropriate statistical methods and rigorous model validation strategies to assess model performance and generalizability, including held-out test datasets and quantitative performance metrics such as IoU and F1 score.
• Develop computational workflows to integrate and analyze data across multiple imaging and spatial modalities, including H&E, multiplex immunofluorescence, spatial proteomics, and spatial transcriptomics.
• Develop Python-based tools and scripts to automate image and data-processing workflows and address interoperability challenges across imaging platforms, analysis tools, and data formats.
• Partner closely with pathologists and discovery scientists to perform rigorous quality control, interpret image analysis outputs, and ensure that quantitative results are biologically meaningful.
• Apply strong analytical and problem-solving skills to troubleshoot complex image and data analysis challenges and deliver high-quality results within established timelines.
• Serve as a subject matter expert in computational digital pathology, providing scientific and technical guidance on image analysis strategies, methodologies, and applications across multidisciplinary project teams.
• Stay current with emerging advances in AI, computer vision, and computational pathology, and evaluate and implement new methodologies that can enhance pathology-driven drug discovery.
• Communicate analytical strategies, methodologies, and results clearly and effectively to scientific and cross-functional stakeholders through written and oral presentations.
• Maintain accurate and reproducible documentation of analytical workflows, algorithms, and results in electronic laboratory notebooks and project reports.
• Work independently and collaboratively within multidisciplinary teams to advance project objectives and deliver high-quality scientific results.

Qualifications

• PhD in computational biology, biomedical engineering, computer science, artificial intelligence, machine learning, computer vision, biomedical image analysis, or related quantitative discipline, with 4+ years of relevant applied experience.
• Strong foundation in mathematics, statistics, image processing, computer vision, and machine learning, with demonstrated experience developing computational methods and algorithms for quantitative image analysis.
• Demonstrated expertise in developing, optimizing, and validating image analysis and machine-learning approaches to extract quantitative features from H&E, immunohistochemistry, and/or multiplexed tissue imaging datasets.
• Strong proficiency in Python for scientific computing, image analysis, and machine learning, with experience using relevant libraries and frameworks such as NumPy, pandas, SciPy, scikit-learn, OpenCV, PyTorch, TensorFlow, or similar. Experience with R is desirable.

• Experience analyzing high-dimensional multiplexed imaging datasets, such as multiplex immunofluorescence, or imaging mass cytometry (IMC), including cell segmentation, cell phenotyping, feature extraction, and spatial analysis.
• Experience developing reproducible and well-documented computational workflows, including version-controlled code, structured data organization, and appropriate documentation of analytical methods and parameters.
• Experience with digital pathology image analysis platforms, such as Visiopharm and QuPath, with the ability to develop customized computational approaches when existing tools do not adequately address the scientific question.
• Excellent analytical, problem-solving, and communication skills, with demonstrated ability to work effectively across multidisciplinary teams and communicate complex computational concepts to scientific collaborators from diverse backgrounds.

Preferred Qualifications

• Strong background in immunology and tissue biology, or demonstrated experience applying computational image analysis to immunologic diseases. Experience with rheumatoid arthritis, inflammatory bowel disease, or related inflammatory conditions is particularly desirable.
• Strong understanding of spatial omics technologies and molecular pathology techniques, including immunohistochemistry, immunofluorescence, in situ hybridization, and related tissue-based assays.
• Experience integrating and analyzing multimodal spatial datasets, including combinations of histopathology, spatial proteomics, and spatial transcriptomics.
• Experience with contemporary computational pathology approaches, including deep learning, representation learning, or related AI-based methods for extracting biologically meaningful information from tissue images.
• Familiarity with cloud-based and/or high-performance computing environments, including AWS or similar computing infrastructure.
• Proficiency with data analysis and visualization tools, such as GraphPad Prism, Spotfire, Excel, or similar applications.
• Demonstrated curiosity and commitment to continuous learning and innovation, with an openness to new ideas, methodologies, and technologies and the ability to translate innovative approaches into practical scientific solutions.
• Self-motivated and highly collaborative, with a strong sense of ownership, scientific integrity, and commitment to quality.

AbbVie is an equal opportunity employer and is committed to operating with integrity, driving innovation, transforming lives and serving our community. Equal Opportunity Employer/Veterans/Disabled.