Principal Biostatistician - Biomarker - open to various countries in Europe (AI/Neural Networks/Deep Learning/Python is a must)

Overview

Principal Biostatistician focused on biomarker research within clinical and biomarker studies, providing statistical leadership and AI/ML expertise across projects.

What you'll do

• Collaborate with representatives from other functions to plan, execute and analyze all biomarker aspects (including genomics) of clinical studies or biomarker studies, acting as project biomarker statistician under guidance of an experienced statistician.
• Develop the Biomarker Evaluation Plan for the study as appropriate, ensuring overall consistency within and between projects.
• Provide statistical input in clinical development discussions, and usage of AI and ML approaches.
• Facilitate the overall organization and coordination of statistical activities regarding biomarker research and development activities for specific studies and projects.
• Conduct and design advanced data analysis for genomics and biomarker statistics, including statistical programming, and design complex analysis algorithms.
• Handle RNA, Olink and other biomarker data.
• Assume responsibility for the production and accuracy of the Biomarker Evaluation Report with respect to statistical deliverables and interpretation of the results.
• Work independently on routine and complex statistical questions, modeling and tasks.
• Develop and implement standard processes for the analysis of routine (parts of) biomarker assessments.

What you'll need

• PhD or MSc in Biostatistics, Statistics or Mathematics, or related field.
• Proven experience developing and deploying deep learning models with PyTorch, TensorFlow or Keras.
• Solid understanding of ML algorithms and statistical methods (incl. survival analysis, batch-effect handling) and their application in pharma/biomarker discovery.
• Explainable AI (SHAP, attention attribution, counterfactuals) and uncertainty quantification for biomarker interpretability.
• Usage of AI and ML approaches.
• Strong Python skills and data manipulation experience (Pandas, NumPy, scikit-learn); production-quality, version-controlled code.
• Strong communication and interpersonal skills.
• Ability to work independently as well as collaboratively, as required.
• Minimal supervision required.
• Previous experience in independently leading biomarker study (mandatory).
• Good knowledge of statistical programming languages including R (Bioconductor package and other relevant R packages for genetic data) and Python.
• Analysis of high-dimensional data.
• Strong knowledge of biomarker evaluation, especially in immunology and infections, type I diabetes, relevant parameters and underlying biology.

Nice to have

• Previous clinical trial experience; industry experience is preferred.

Details

• Location: ESP-Remote (Madrid); open to various countries in Europe.