Senior Data Scientist

Grifols•San Carlos, CA

1d•Onsite

About The Position

Grifols is seeking a Senior Data Scientist to execute clinical biostatistics and machine learning projects supporting stakeholders across Alkahest Data Science, Alkahest Proteomics, Plasma R&D, and Biosupplies. The role leads and advises on data analysis for the setup, evaluation, and interpretation of longitudinal and high-dimensional omics and real-world evidence datasets. Areas of specialization include longitudinal multivariate analysis, linear mixed models, dimensionality reduction, prediction modeling, survival analysis, causal inference, and modern AI methods such as foundation models and multimodal learning applied to large-scale omics and real-world datasets. This is primarily an individual-contributor role. The Senior Data Scientist independently selects methods, techniques, and evaluation criteria; contributes to scientific and technical advances; publishes and presents research; and may mentor other biostatisticians and data scientists. The role works across functions and disciplines, advises internal stakeholders, and represents the organization in scientific settings. The work is performed in an office environment with exposure to electrical office equipment. The position frequently involves sitting for 6–8 hours per day, frequent hand movements, occasional walking and standing, occasional neck bending and twisting, and lifting or carrying objects up to 25 pounds. Frequent driving to site locations and occasional travel within the United States are required.

Requirements

Ph.D.; alternatively, depending on the assignment, a BA/BS or advanced degree with at least 12 years of advanced experience may be considered.
Typically 8 or more years of relevant experience.
Expert knowledge of scientific principles and concepts in the relevant discipline.
Strong background in statistics, machine learning, deep learning, and AI methodologies, including linear and nonlinear modeling, multivariate analysis, causal inference, network analysis, algorithm development, representation learning, foundation models, multimodal learning, and model interpretability.
Experience applying foundation models, transfer learning, and modern AI approaches to large-scale biomedical, clinical, omics, imaging, and real-world datasets.
Excellent statistical programming skills in Python and R.
Demonstrated experience analyzing proteomics combined with other large-scale data, such as genomics, real-world data, RNA sequencing, and imaging.
Significant experience working with preclinical or clinical study data.
Ability to exercise independent judgment in developing methods, techniques, and evaluation criteria.
Ability to explain difficult concepts and influence others.
Excellent written and oral communication skills.
Ability to draw conclusions from novel research and create solutions to critical new problems.
Ability to communicate and understand information presented verbally and in writing, relate sensitive information to diverse groups, and work with diverse groups to reach consensus.

Responsibilities

Execute cross-functional scientific study designs and projects that contribute to the direction of the department or discipline.
Apply professional concepts and develop methods to address problems, including identifying novel therapeutic targets and biomarkers for disease diagnosis, risk, and progression prediction.
Ensure the completeness, critical evaluation, correctness, and integrity of datasets and analyses.
Conduct integrative analysis of Alkahest and Grifols datasets, including independent studies with significant impact.
Serve as an internal contact for preclinical and clinical data science and biostatistics.
Contribute to the development and application of machine learning, deep learning, and AI technologies, including foundation models and multimodal approaches for biological, clinical, and real-world data.
Build cross-functional networks with peers and key decision-makers and serve as an internal spokesperson for the organization in the relevant function.
Attend and participate in national and international scientific meetings.
May mentor biostatisticians and data scientists to improve the quality and quantity of their work.
Select methods, techniques, and evaluation criteria autonomously to obtain results.
Achieve measurable accomplishments that advance the scientific or technical field.
Author abstracts, posters, and peer-reviewed papers; contribute regularly to scientific literature and develop external recognition.
Monitor and evaluate the completion of tasks and projects.