Principal Scientist, Computational Biology-Oncology Translational Research

Johnson & Johnson•La Jolla, PA

1d•Hybrid

About The Position

The Principal Scientist, Computational Biology-Oncology Translational Research, will be responsible for developing and executing computational strategy for oncology translational and clinical biomarker programs. This individual will lead the integration and interpretation of complex multimodal omics, biomarker, and clinical data; determine and defend fit-for-purpose analytical approaches; and deliver rigorous AI-enabled bioinformatics, statistical, and machine-learning evidence that meaningfully informs clinical development. The role requires broad oncology expertise, deep clinical-trial and pharmaceutical-development knowledge, and the scientific leadership to influence decisions across Translational Research, Clinical Development, Statistics, Programming, Pathology, Diagnostics, Data Science, Regulatory, and Biomarker Operations.

Requirements

PhD in Bioinformatics, Computational Biology, Biostatistics, Genomics, Data Science, or a related quantitative field, with at least 3 years of relevant pharmaceutical or biotechnology industry experience.
Advanced proficiency in R, with experience in Python, Linux/Unix, shell scripting, version control, and reproducible analysis of high-throughput sequencing and multimodal omics data.
Demonstrated scientific leadership in computational oncology, with deep knowledge of cancer biology, biomarker applications, oncology drug development, and the ability to facilitate major programs or study workstreams.
Advanced statistical and machine-learning experience, including regression, multivariate data analysis, survival analysis, supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning for the analysis of biomarker, assay, and clinical data.
Deep working knowledge of IND and NME development and Phase 1–3 oncology trials, including dose escalation and expansion, randomization, stratification, analysis populations, clinical endpoints, censoring, longitudinal data, and treatment response.
Ability to lead and influence across functions, communicate and defend complex analytical recommendations and limitations, mentor others, and demonstrate scientific impact through high-quality peer-reviewed publications and presentations.

Nice To Haves

Deep working knowledge of CDISC SDTM and ADaM data models, regulatory clinical data management practices, and biomarker-data traceability.
Experience with deep learning, multimodal modeling, or responsible application of foundation models or agentic AI to biomedical research.
Working knowledge of clinical-trial statistics approaching an effective partnership level with clinical statisticians, including survival and longitudinal models, multiplicity, missingness, treatment-effect heterogeneity, and external validation.
Experience supporting patient-selection, companion or complementary diagnostic, regulatory, or submission-related biomarker activities.

Responsibilities

Lead computational hands-on analyses of multimodal oncology biomarker data, including DNA/RNA sequencing, proteomics, flow cytometry, single-cell, and spatial transcriptomics data; apply deep cancer biology knowledge to determine and defend analytical approaches and biological interpretation.
Define and develop appropriate statistical and machine-learning plans to carry out biomarker and clinical-outcome analyses, with careful consideration of validation, bias, missingness, batch effects, and analytical limitations.
Drive integration of molecular, pathological, assay, sample, and clinical data to establish the relevance, clinical utility, evidentiary strength, and limitations of pharmacodynamic, prognostic, predictive, and resistance biomarkers.
Define and support computational evidence generation for biomarker plans, patient-selection and enrichment strategies, MRD initiatives, longitudinal monitoring, and clinical-study interpretation using deep knowledge of oncology drug development and trial design.
Drive responsible adoption of approved AI-enabled methods, including multimodal and foundation-model approaches and agentic workflows; ensure human oversight, validation, traceability, reproducibility, data privacy, and scientific accountability.
Collaborate with cross-functional study and program teams; make and defend computational recommendations; and contribute to publications, presentations, and evaluation of emerging computational and biomarker technologies.

Benefits

Consolidated retirement plan (pension)
Savings plan (401(k))
Long-term incentive program
Vacation –120 hours per calendar year
Sick time - 40 hours per calendar year (varies by state)
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 the birth/adoption/foster care of a child
Bereavement Leave – 240 hours for an immediate family member: 40 hours for an extended family member 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