Principal Data Scientist – R&D DSDH - Preclinical Sciences & Translational Safety (PSTS)
Johnson & Johnson
5 months ago
Remote friendly (San Diego, CA)
United States
Clinical Research and Development
Principal Data Scientist – R&D DSDH - Preclinical Sciences & Translational Safety (PSTS)
Position Summary
- Leverage machine learning and data engineering to create AI-ready datasets, develop predictive models, and deliver analytics that improve safety evaluations and facilitate translational research.
Key Responsibilities
- Develop/deploy ML/AI models for safety signal detection, dose selection, PK/PD modeling, toxicology insights, and translational interpretation.
- Implement representation learning, predictive modeling, and multivariate analytics across in vivo, in vitro, exposure-response, and pathology data.
- Build scalable data pipelines integrating PSTS-relevant sources and transform experimental outputs into standardized, analysis-ready, AI-ready datasets.
- Collaborate with toxicology/DMPK/safety stakeholders to translate study designs into computational requirements and improve cross-study comparability (terminologies, metadata, quality checks).
Qualifications
Required:
- MS or PhD in Data Science, Computational Biology, Toxicology, Pharmacology, Biomedical Engineering, Computer Science, or related.
- 3+ years applying ML and/or data engineering to scientific/biomedical datasets.
- Proficient in Python and/or R, SQL, and modern data engineering tools (cloud, workflow orchestration, version control).
- Experience with ML model development/evaluation/deployment pipelines.
- Experience with biological/toxicology/PK/PD/in vivo datasets.
Preferred
- Safety sciences, ADME/DMPK, toxicogenomics, biomarker analytics; familiarity with scientific data formats; ontologies/semantic technologies/knowledge graphs; AWS S3/Snowflake/Redshift; SEND/CDISC.
Benefits (time off)
- Vacation 120h/yr; Sick 40h/yr (CO 48h; WA 56h); Holiday incl. floating 13 days/yr; Work/Personal/Family up to 40h/yr; Parental leave 480h; Bereavement 240h; Caregiver leave 80h; Volunteer 32h; Military spouse time-off 80h.
Application Instructions
- Apply for Europe-based locations using Req. R-069190.
Position Summary
- Leverage machine learning and data engineering to create AI-ready datasets, develop predictive models, and deliver analytics that improve safety evaluations and facilitate translational research.
Key Responsibilities
- Develop/deploy ML/AI models for safety signal detection, dose selection, PK/PD modeling, toxicology insights, and translational interpretation.
- Implement representation learning, predictive modeling, and multivariate analytics across in vivo, in vitro, exposure-response, and pathology data.
- Build scalable data pipelines integrating PSTS-relevant sources and transform experimental outputs into standardized, analysis-ready, AI-ready datasets.
- Collaborate with toxicology/DMPK/safety stakeholders to translate study designs into computational requirements and improve cross-study comparability (terminologies, metadata, quality checks).
Qualifications
Required:
- MS or PhD in Data Science, Computational Biology, Toxicology, Pharmacology, Biomedical Engineering, Computer Science, or related.
- 3+ years applying ML and/or data engineering to scientific/biomedical datasets.
- Proficient in Python and/or R, SQL, and modern data engineering tools (cloud, workflow orchestration, version control).
- Experience with ML model development/evaluation/deployment pipelines.
- Experience with biological/toxicology/PK/PD/in vivo datasets.
Preferred
- Safety sciences, ADME/DMPK, toxicogenomics, biomarker analytics; familiarity with scientific data formats; ontologies/semantic technologies/knowledge graphs; AWS S3/Snowflake/Redshift; SEND/CDISC.
Benefits (time off)
- Vacation 120h/yr; Sick 40h/yr (CO 48h; WA 56h); Holiday incl. floating 13 days/yr; Work/Personal/Family up to 40h/yr; Parental leave 480h; Bereavement 240h; Caregiver leave 80h; Volunteer 32h; Military spouse time-off 80h.
Application Instructions
- Apply for Europe-based locations using Req. R-069190.