Scientist, Data Science

Scientist Position in Early Oncology R&D

We are seeking a highly motivated scientist to join a newly formed, dynamic team within early oncology R&D. The successful candidate will leverage their data science expertise in mining large datasets to drive our efforts in target identification, mechanism of action (MOA) studies, and biomarker strategy development, with a particular focus on analyses related to the function and aging of the immune system.

At AstraZeneca, you'll have the opportunity to make a significant impact on the future of healthcare while working in a collaborative environment at the cutting edge of research. The ideal candidate will thrive in this setting, contributing to our growth trajectory as we build our evolving team.

• Execute and Maintain Pipelines:
  Process and analyze large-scale biobank datasets, human population data, and in-vitro biological data using established analysis pipelines.
• Analytical Support:
  Apply analytical methods and machine learning algorithms to help identify potential therapeutic targets and biomarkers.
• Cross-Functional Collaboration:
  
  Partner with wet-lab scientists to analyze experimental results for target identification and Mechanism of Action (MOA) studies.
• Data Visualization:
  Generate high-quality visualizations and reports to communicate findings to the project team.
• Strategic Contribution:
  Provide high-quality data and computational insights that contribute to the development of biomarker strategies.
• Team Participation:
  Actively participate in team meetings, presenting data-driven insights to help the group meet project milestones.
• Continuous Learning:
  Stay current with the latest developments in data science and bioinformatics tools.

• Education:
  
  Ph.D. in Bioinformatics, Computational Biology, Data Science, Epidemiology, or a related field (0–2 years post-graduate experience); or MS with 2–4 years of experience; or BS with 4+ years of relevant experience.
• Data
  
  Experience:
  
  Minimum 2 years of experience working with large-scale biological or population datasets, preferably including experience analyzing immune system aging/function within the context of human and/or mouse data.
• Coding Proficiency:
  Strong proficiency in Python or R.
• Technical Knowledge:
  Solid understanding of statistical analysis and foundational machine learning techniques.
• Genomics Foundation:
  Hands-on experience with NGS data analysis (e.g., RNA-seq, DNA methylation, ChIP-seq, or ATAC-seq).
• Multi-omics Interest:
  Experience with, or a strong desire to learn, proteomic data analysis and multi-omic data integration.
• Operational
  
  Skills:
  
  Excellent problem-solving skills, attention to detail, and the ability to manage multiple tasks in a fast-paced environment.
• Communication:
  Ability to clearly present data and technical workflows to a multidisciplinary team.

• Prior experience or familiarity with biomarkers of immune system aging/function.
• Prior experience or internship in the pharmaceutical or biotechnology industry.
• Prior experience running large-scale association testing (e.g., genome-wide association studies [GWAS], epigenome-wide association studies [EWAS], proteome-wide association studies).
• Familiarity with methods in statistical genetics (e.g., Mendelian randomization, fine mapping, colocalization).
• Familiarity with machine learning analysis architectures (e.g., random forest, gradient boosting, transformers).
• Familiarity with public biological databases (e.g., GTEx, TCGA), epidemiological cohort data (e.g., TOPMed cohorts), or biobanks (e.g., UK Biobank, Finn Gen).
• Ability to apply integrated generative protein design pipelines - from target-conditioned backbone generation through sequence design to computational fold validation - to support the development of novel therapeutic biologics with optimized specificity and develop ability properties.
• Working knowledge of computational histology pipelines incorporating modern deep learning approaches - including self-supervised and weakly supervised learning (MIL, DINO) and histopathology foundation models (e.g. UNI, CONCH) - to enable scalable, label-efficient classification of complex tissue…