Principal Data Scientist – R&D DSDH - Therapeutics Discovery; TD

Principal Data Scientist – R&D DSDH - Therapeutics Discovery (TD)
Responsibilities

• Develop ML/AI models that support discovery workflows, including target prioritization, multi-omics integration, and mechanistic inference.
• Apply modern ML approaches (deep learning, graph learning, foundation models, generative models) to chemical, biological, imaging, and assay datasets.
• Build and optimize models for real-world R&D use cases, ensuring scalability, interpretability, and scientific rigor.
• Design, build, and maintain robust data pipelines to curate, standardize, and integrate diverse R&D datasets (chemical, biological, multi-omics, imaging, biophysical, automation logs, etc.).
• Partner with platform teams to implement best-practice MLOps/Dev Ops workflows and deploy ML models into production R&D environments.
• Develop tooling to accelerate dataset preparation, feature engineering, and model lifecycle management across TD.
• Work with TD scientists to understand key biological/chemical questions and shape computational strategy.
• Translate sparse, heterogeneous experimental data into insights for hit discovery, mechanism studies, perturbation experiments, and compound optimization.
• Participate in design, interpretation, and iterative refinement of discovery experiments.
• Partner cross-functionally (R&D Data Science, IT, platform engineering, therapeutic area groups) to drive AI/ML adoption.
• Contribute to evaluating new analytical methods, automation technologies, and data platforms; champion data quality, documentation, governance, and reproducibility.

• Master’s or Ph.D. in Computational Biology, Bioinformatics, Data Science, Chemistry, Chemical Biology, Biomedical Engineering, Computer Science, or related field.
• Experience applying ML/AI in scientific domains (drug discovery, biology, chemistry, systems biology, imaging, etc.).
• Strong Python programming skills (preferred) and experience with ML/scientific libraries (PyTorch, Tensor Flow, scikit-learn, RDKit, etc.).
• Data engineering experience: data modeling, workflow orchestration, ETL/ELT pipelines, and cloud computing (AWS, GCP, or Azure).
• Ability to work directly with experimental scientists to solve real R&D challenges.

• Pharma/biotech discovery experience (target assessment, phenotypic screening, medicinal chemistry workflows, lab automation).
• Familiarity with omics, high-content imaging, chemical structure data, and/or biological assay data.
• Knowledge of data standards (e.g., FAIR, ontologies, controlled vocabularies) and regulated/quality-governed environments.
• Strong communication skills; ability to thrive in a matrixed, multidisciplinary environment.

• Advanced Analytics
• Critical Thinking
• Data Analysis
• Data Quality
• Data Reporting Data Science
• Data Visualization
• Digital Fluency
• Process Improvements
• Strategic Thinking
• Technical Credibility
• Workflow Analysis

• Coaching
• Econometric Models
• Organizing
• Data Privacy Standards
• Data Savvy

• Vacation: 120 hours per calendar year
• Sick time: 40 hours per calendar year (CO: 48; WA: 56)
• Holiday pay (including floating holidays): 13 days per calendar year
• Work, Personal and Family Time: up to 40 hours per calendar year
• Parental Leave: 480 hours within one year of birth/adoption/foster care
• Bereavement Leave: 240 hours immediate family; 40 hours extended family per calendar year
• Caregiver Leave: 80 hours in a 52-week rolling period
• Volunteer Leave: 32 hours per calendar year
• Military Spouse Time-Off: 80 hours per calendar year