Senior Scientist, Translational Data Science

AstraZeneca•Cambridge, MA

20h•$115,058 - $178,586•Hybrid

About The Position

We are looking for an experienced Translational Data Scientist to join our Data Science and Bioinformatics team, specifically within the Translational Medicine and Bioinformatics department in the Immunology therapeutic area. This role is based in Kendall Square, Boston. You will be part of a highly collaborative and science-driven environment focused on advancing our understanding of immune-mediated disease biology, identifying novel therapeutic opportunities, and enabling precision approaches across our Immunology portfolio from discovery through clinical development. The department fosters an open and collaborative atmosphere, with a culture that is both science-based and patient-focused, aiming to understand disease mechanisms at the molecular and cellular level, identify effective targets, biomarkers, and patient subgroups, and support the translation of scientific discoveries into life-improving medicines. In this role, you will work with specialists in immunology, cell therapy, translational medicine, and data science, as well as other translational data scientists and AI experts. You will enable translational science through the integration and interpretation of large-scale multimodal datasets, with a particular emphasis on single-cell and spatial omics in immunology. You will apply innovative analytical and AI-driven approaches to identify disease mechanisms, therapeutic hypotheses, biomarkers, and patient subgroups, supporting decision-making across the portfolio and contributing to the identification of transformational precision medicine propositions. Your responsibilities will include planning, performing, interpreting, and communicating analyses that maximize the value of data assets such as single-cell transcriptomics, spatial transcriptomics, BCR/TCR repertoire data, high-dimensional immune profiling data, and other complementary molecular and clinical datasets. You will also play a central role in evaluating, adopting, and applying AI and machine learning methodologies, including hands-on experience with large language models, biological foundation models, and other frontier AI approaches. Critically, you will act as a scientific guide and quality arbiter for AI outputs, ensuring biological validity and translational relevance. By applying state-of-the-art computational methods, you will help generate actionable biological insight in immunological diseases and support the advancement of next-generation therapeutic strategies, including cell therapy.

Requirements

Relevant PhD (or equivalent) in computational biology, translational data science, bioinformatics, biostatistics, or a related quantitative discipline.
At least 3+ years of relevant applied experience in academia, biotech, or pharmaceutical R&D.
Deep expertise in single-cell omics analysis, with strong hands-on experience in the analysis, interpretation, and biological application of single-cell RNA-seq data.
Strong experience in spatial omics / spatial transcriptomics / spatial proteomics.
Expertise in at least one of BCR/TCR repertoire analysis or high-dimensional cytometry data analysis such as CyTOF, together with interest in working across both.
Proven experience in multimodal data integration across molecular and clinical datasets, especially across modalities such as single-cell transcriptomics, spatial omics, immune repertoire data, cytometry, and associated metadata.
Excellent coding skills in Python, R, or similar languages appropriate for large-scale omics analysis.
Experience in version control such as Git/Bitbucket.
Experience in Linux environments (cluster and/or cloud).
Effective use of modern AI-assisted coding tools such as GitHub Copilot or Claude Code.
Strong understanding of immunology and the use of omics data to derive biological insight relevant to disease mechanisms, translational research, biomarker strategies, and therapeutic development.
Demonstrated hands-on experience applying machine learning and AI methods to biological data, including familiarity with at least one of: biological foundation models (e.g. scGPT), deep learning frameworks (PyTorch or TensorFlow), large language models for biological knowledge extraction or agentic workflows, or generative and representation learning approaches.
Ability to critically evaluate AI tool outputs in a biological and translational context.
Outstanding communication and collaboration skills, with the ability to explain complex computational analyses to both expert and non-expert audiences and to work effectively across cross-functional teams.
A high degree of scientific independence, curiosity, and a proactive, delivery-focused mindset.

Nice To Haves

Experience in Immunology and/or Cell Therapy research within a pharmaceutical, biotech, or leading academic environment.
Experience with both BCR/TCR repertoire analysis and CyTOF.
Experience working within AI-augmented analytical pipelines and the ability to define when and where AI adds genuine scientific value versus where human biological judgement remains essential.
Track record of applying translational data science and computational analyses to drive decisions in drug discovery, translational science, or clinical development.
Experience leading projects and collaborating with internal and/or external partners in matrixed, multidisciplinary teams.

Responsibilities

Integrate and interpret large-scale multimodal datasets, with emphasis on single-cell and spatial omics in immunology.
Apply innovative analytical and AI-driven approaches to identify disease mechanisms, therapeutic hypotheses, biomarkers, and patient subgroups.
Support decision-making across the portfolio by providing data-driven insights.
Contribute to the identification of transformational precision medicine propositions.
Plan, perform, interpret, and communicate analyses of data assets including single-cell transcriptomics, spatial transcriptomics, BCR/TCR repertoire data, high-dimensional immune profiling data, and complementary molecular and clinical datasets.
Evaluate, adopt, and apply AI and machine learning methodologies, including large language models and biological foundation models.
Act as a scientific guide and quality arbiter for AI outputs, ensuring biological validity and translational relevance.
Generate actionable biological insight in immunological diseases.
Support the advancement of next-generation therapeutic strategies, including cell therapy.