Senior Data Scientist, Biologics Discovery - Madrid, ES

Description

The company develops biologic medicines. This role sits in the Data Science team within Biologics Discovery and works closely with In Silico Discovery (ISD), which builds the molecular design and property-prediction models that decide which biologic candidates are designed, made and advanced.

ISD owns core molecular model development. You would build the data-side machine learning work, such as featurization and model-ready datasets, that makes ISD's models quicker to build and easier to trust.

Biologics Discovery produces fast-growing data from assays, sequences and modalities. The goal is to make that data fully ready for modeling and easy to use for ML, and to apply ML to help scientists rank molecules, spot risks and form hypotheses earlier, supporting ISD's models rather than duplicating them.

You will design featurization methods and build standardized, traceable, model-ready datasets from biologics assay, biophysical, sequence and construct data. You will work between the data-generating teams, the data infrastructure partners and ISD, so your datasets and features strengthen ISD's molecular property models. The role offers room to grow your scope, technical leadership and impact as you deliver results.

Responsibilities

• Explore, combine and characterize varied biologics discovery data, such as antibody and protein sequences, constructs, assays and biophysical measurements, using current data science tools.
• Turn scientific questions and design-make-test-learn (DMTL) decision points into clear data and analysis requirements with discovery scientists.
• Identify data quality problems, bias, gaps and risks, including leakage and distribution shift, that could affect modeling or interpretation.
• Help teams use data to prioritize molecules, identify risks and generate hypotheses.
• Specify with data engineers the features, labels and aggregation levels that models need, keeping raw representations where they carry important information.
• Build featurization and model-ready datasets, and curate, document and version them so modeling stays reproducible and traceable.
• Hand off standardized, traceable training datasets to ISD and agree on which modeling work belongs to Data Science and which belongs to ISD.
• Frame ML problems around real DMTL decisions together with discovery scientists.
• Work with ontology and MLOps colleagues so datasets carry consistent meaning and models move reliably into use.
• Promote reproducibility, documentation and responsible AI.

Requirements

• Required: a Master's or Ph.D. in Computer Science, Machine Learning, Computational Biology, Bioinformatics, Statistics or a related field.
• Required: at least 2 years of applied ML experience, including model development, evaluation and dataset curation on complex scientific or biomedical data.
• Required: strong Python skills, the modern ML stack such as PyTorch or scikit-learn, and SQL.
• Required: experience turning complex, heterogeneous experimental data into robust features and training sets, with exposure to cloud training and data infrastructure.
• Required: a sound understanding of evaluation and validation, and of the risks of leakage and distribution shift.
• Required: the ability to work effectively with experimental scientists and modeling partners in a matrixed R&D environment.
• Preferred: experience with biologics, antibody or protein sequence models, or protein language models.
• Preferred: experience with active learning, Bayesian optimization or sequence-based generative models for molecular design.
• Preferred: familiarity with biophysical or assay data and developability endpoints.
• Preferred: experience with MLOps, experiment tracking and model monitoring.
• Preferred: familiarity with how ontologies or knowledge graphs support data reuse and AI-ready datasets.
• Preferred skills: advanced analytics, business intelligence (BI), coaching, collaboration, critical thinking, data analysis, database management, data privacy standards, data reporting, data savvy, data science, data visualization, econometric models, process improvements, technical credibility, technologically savvy, workflow analysis.

Conditions

Based at one of the office locations in Spring House, PA (strongly preferred), Titusville, NJ, or Raritan, NJ, USA, or in Madrid, Spain.

No remote option.

The role is posted under separate requisition numbers by country: R-095854 for the USA and R-096793 for Spain.

Anticipated base pay range: €55,400.00 - €87,860.00.

The company provides an inclusive workplace and respects the diversity, dignity and merit of its employees.

Benefits

• An annual bonus with a set target percentage of pay, which depends on pay grade and location and is based on company and individual performance in the previous calendar year, or sales commissions where applicable.
• Vacation days.
• Parental leave of at least 12 weeks, along with bereavement, caregiver and volunteer leave.
• Well-being reimbursement and programs for financial, physical and mental health.
• Service anniversary and recognition awards.
• Insurance plans, subject to plan terms, for employees and, in some locations, eligible dependents.
• Details are on the company's benefits page. Amounts and benefits vary by location and may change, and the list is for information only.