Senior AI Data Scientist I

Exelixis•Alameda, CA

3d•$143,500 - $203,000•Onsite

About The Position

The Senior AI Data Scientist I develops, trains and validates AI/ML models and analytics solutions that transform complex clinical datasets into analysis-ready deliverables supporting drug-development decisions. Leveraging statistical programming (R, Python, SQL) and machine-learning techniques, this role executes automated workflows, data quality assurance, and regulatory-compliant outputs within a GxP-governed clinical data pipeline. This position exists to advance the organization's AI/ML and data science capabilities across clinical development - collaborating with Statistical Programming, Clinical Data Management, and Clinical Operations to accelerate data-driven insights, improve data infrastructure, and ensure the accuracy and reproducibility of analytical outputs that inform study-level and portfolio-level decisions.

Requirements

Bachelor's degree in Data Science, Computer Science, Statistics, Biostatistics, Bioinformatics, or a related quantitative field and a minimum of 7 years of experience; or, Master's degree in Data Science, Computer Science, Statistics, Biostatistics, Bioinformatics, or a related quantitative field and a minimum of 5 years of experience; or, Equivalent combination of education and experience.
With PhD: No prior experience applying AI/ML methods to structured or unstructured data.
With Master's degree: A minimum of one (1) year of experience applying AI/ML methods to structured or unstructured data.
With Bachelor's degree: A minimum of three (3) years of experience applying AI/ML methods to structured or unstructured data.
Without degree: A minimum of seven (7) years of relevant professional experience, including demonstrated application of AI/ML methods to structured or unstructured data.
Intermediate proficiency in Python (Pandas, NumPy, scikit-learn) for data manipulation and model prototyping.
Intermediate proficiency in R for statistical analysis and visualization.
Basic proficiency in SQL for data querying and transformation.
Intermediate understanding of supervised and unsupervised learning fundamentals, including model evaluation.
Basic familiarity with NLP, text mining and/or time series analysis techniques.
Basic familiarity with LLM APIs and prompt engineering concepts.
Basic knowledge of Databricks notebooks and Delta Lake concepts.
Basic familiarity with AWS cloud services (S3, Lambda, Glue).
Basic understanding of data pipeline concepts and data integration fundamentals.
Intermediate proficiency with version control (Git/GitHub) and project tracking tools (Jira).
Intermediate proficiency with BI platforms including Spotfire, Tableau and/or Power BI.
Basic understanding of the clinical development process and regulatory requirements (ICH, GxP).
Basic familiarity with CDISC data standards (SDTM, ADaM) concepts.
Ability to communicate technical concepts clearly to diverse audiences.
Strong collaboration and teamwork skills in a cross-functional environment.
Attention to detail and organizational skills.

Responsibilities

Build, train and validate machine-learning models (supervised and unsupervised) on clinical datasets under the direction of senior data scientists, ensuring model performance meets predefined acceptance criteria.
Execute data cleaning, transformation, and standardization tasks across clinical datasets from EDC, vendor and real-world data sources, aligning outputs with CDISC (SDTM/ADaM) standards.
Develop and maintain LLM-based and generative AI-workflows for automated TLF review and ad-hoc analytical queries, applying human-in-the-loop validation to ensure output reliability.
Create interactive dashboards and visualizations that support clinical data review, study-health monitoring, and decision-making across cross-functional stakeholders.
Execute data validation checks and quality-assurance procedures to ensure accuracy, reproducibility and compliance of analytical outputs with GxP requirements.
Support the development and maintenance of data pipelines on Databricks and AWS cloud infrastructure, applying version control (Git/GitHub) and CI/CD best practices.
Collaborate with Statistical Programming, Clinical Data Management, and Clinical Operations to deliver AI/ML project milestones and address study-level data needs.
Prepare and maintain documentation of model development, data transformation, and validation activities consistent with SOPs and work instructions.
Drive external scientific visibility and publication objectives by contributing to manuscripts, conference presentations and white papers that showcase clinical AI/data science innovations.
Pursue continuous professional development in emerging AI/ML techniques, cloud-based data platforms, and clinical data science methodologies to advance team capabilities.
Performs other duties as assigned
Complies with all policies and standards