Senior Data Scientist, Biologics Discovery
Johnson & Johnson
September 01, 2026
On-site
Spring House, PA
Clinical Research and Development
About The Opportunity
Senior Data Scientist (Biologics Discovery) on Data, Data Science & Artificial Intelligence (DDSAI), partnering with In Silico Discovery (ISD) to build data-facing ML capabilities that make ISD molecular models faster and more trustworthy.
Position Summary
Design featurization and dataset curation, build/evaluate applied models on biologics assay, biophysical, and sequence/construct data, and define evaluation frameworks to keep models trustworthy.
Key Responsibilities
- Develop featurization and model-ready datasets from antibody/protein sequence, construct, assay, and biophysical data.
- Specify features/labels/aggregation levels with data engineers; preserve raw representations where needed.
- Curate, document, and version datasets for reproducibility/traceability.
- Collaborate with ISD on standardized, traceable training datasets and DS vs. ISD ownership boundaries.
- Partner with discovery scientists to frame ML around real decision points in the DMTL cycle.
- Work with ontology and MLOps colleagues to align dataset semantics and reliable model deployment.
- Champion reproducibility, documentation, and responsible AI.
Qualifications
Required:
- Master’s or Ph.D. in CS/ML/Computational Biology/Bioinformatics/Statistics (or related).
- 2+ years applied ML (development, evaluation, dataset curation) on complex scientific/biomedical data.
- Proficiency in Python (PyTorch, scikit-learn) and SQL.
- Experience converting heterogeneous experimental data into robust features/training sets; exposure to cloud training/data infrastructure.
- Knowledge of evaluation/validation and risks of leakage and distribution shift.
- Ability to collaborate in matrixed R&D.
Preferred:
- Biologics/antibody or protein language models.
- Active learning, Bayesian optimization, sequence-based generative models for molecular design.
- Familiarity with biophysical/assay data and developability endpoints.
- MLOps, experiment tracking, model monitoring.
- Ontologies/knowledge graphs for data reuse and AI-ready datasets.
Location/Work:
Spring House, PA (strongly preferred), Titusville, NJ, Raritan, NJ, or Madrid, Spain; no remote option.
Compensation & Benefits (explicit):
- Anticipated base pay range: $109,000–$174,800; eligible for annual performance bonus.
- Benefits include medical/dental/vision, life insurance, short-/long-term disability, retirement plan/401(k), and time off (vacation up to 120 hrs/yr; sick up to 40 hrs/yr; holiday/floating holidays up to 13 days/yr; work/personal/family time up to 40 hrs/yr).
Senior Data Scientist (Biologics Discovery) on Data, Data Science & Artificial Intelligence (DDSAI), partnering with In Silico Discovery (ISD) to build data-facing ML capabilities that make ISD molecular models faster and more trustworthy.
Position Summary
Design featurization and dataset curation, build/evaluate applied models on biologics assay, biophysical, and sequence/construct data, and define evaluation frameworks to keep models trustworthy.
Key Responsibilities
- Develop featurization and model-ready datasets from antibody/protein sequence, construct, assay, and biophysical data.
- Specify features/labels/aggregation levels with data engineers; preserve raw representations where needed.
- Curate, document, and version datasets for reproducibility/traceability.
- Collaborate with ISD on standardized, traceable training datasets and DS vs. ISD ownership boundaries.
- Partner with discovery scientists to frame ML around real decision points in the DMTL cycle.
- Work with ontology and MLOps colleagues to align dataset semantics and reliable model deployment.
- Champion reproducibility, documentation, and responsible AI.
Qualifications
Required:
- Master’s or Ph.D. in CS/ML/Computational Biology/Bioinformatics/Statistics (or related).
- 2+ years applied ML (development, evaluation, dataset curation) on complex scientific/biomedical data.
- Proficiency in Python (PyTorch, scikit-learn) and SQL.
- Experience converting heterogeneous experimental data into robust features/training sets; exposure to cloud training/data infrastructure.
- Knowledge of evaluation/validation and risks of leakage and distribution shift.
- Ability to collaborate in matrixed R&D.
Preferred:
- Biologics/antibody or protein language models.
- Active learning, Bayesian optimization, sequence-based generative models for molecular design.
- Familiarity with biophysical/assay data and developability endpoints.
- MLOps, experiment tracking, model monitoring.
- Ontologies/knowledge graphs for data reuse and AI-ready datasets.
Location/Work:
Spring House, PA (strongly preferred), Titusville, NJ, Raritan, NJ, or Madrid, Spain; no remote option.
Compensation & Benefits (explicit):
- Anticipated base pay range: $109,000–$174,800; eligible for annual performance bonus.
- Benefits include medical/dental/vision, life insurance, short-/long-term disability, retirement plan/401(k), and time off (vacation up to 120 hrs/yr; sick up to 40 hrs/yr; holiday/floating holidays up to 13 days/yr; work/personal/family time up to 40 hrs/yr).