Senior Staff Scientist-Quantitative Modeling, AI & Pharmacometrics

Job Function Summary Applies advanced computational, computer science, data science, statistical, and quantitative modeling principles, together with domain expertise in pharmacology, drug development, and translational science, to perform research and technology development supporting model-informed drug development (MIDD). Responsibilities include the design, development, implementation, validation, and application of computational models, machine learning approaches, simulation frameworks, and quantitative decision‑support tools used to advance drug regimen development and clinical translation. The position integrates diverse preclinical, clinical, and real-world datasets to develop predictive models that support regimen optimization, dose selection, trial design, and translational decision‑making. Research activities may include pharmacometric modeling, quantitative systems pharmacology (QSP), mechanistic and Bayesian modeling, artificial intelligence and machine learning methods, statistical analyses, and development of computational workflows and scientific software. This specialty exists for positions whose primary responsibility is to conduct independent quantitative research and use computational and data science technologies to advance biomedical and translational research. Generic Scope Technical leader with a high degree of knowledge in the overall field and recognized expertise in specific areas; problem‑solving frequently requires analysis of unique issues / problems without precedent and / or structure. May manage programs that include formulating strategies and administering policies, processes, and resources; functions with a high degree of autonomy. Custom Scope The Savic Integrated Pharmacology Laboratory at UCSF seeks a senior quantitative scientist to lead the development and application of advanced computational, statistical, pharmacometric, and machine learning methodologies to support model‑informed drug development (MIDD) within the PReDiCTR‑TB Consortium. The incumbent will apply expertise in pharmacometrics, quantitative systems pharmacology, AI/ML, computational biology, and translational modeling to develop predictive frameworks that inform regimen optimization, dose selection, clinical trial design, and translational decision‑making for infectious disease drug development. The position requires scientific leadership across multiple complex projects and collaboration with academic, industry, and regulatory stakeholders. The incumbent will independently design, develop, validate, and deploy quantitative models and computational tools that integrate preclinical, clinical, and real‑world datasets, and will contribute to publications, grant applications, and strategic scientific initiatives across the consortium. Duties and Essential Job Functions Quantitative Modeling & Simulation (30%) Lead development of PK/PD, mechanistic, Bayesian, QSP, and AI‑enabled models Design predictive frameworks for TB regimen optimization Develop translational strategies linking preclinical and clinical data Computational Research & Data Integration (25%) Integrate multi‑source datasets Develop computational workflows Apply machine learning and statistical methods Scientific Leadership (15%) Guide modeling strategy Collaborate with external investigators Influence scientific decision making Publications, Grants & Scientific Communication (15%) Manuscripts Conference presentations Grant development Mentoring & Technical Leadership (15%) Mentor trainees Lead interdisciplinary project teams Establish best practices Required Qualifications Bachelor's degree in Computer / Computational / Data Science, or Domain Sciences with computer / computational / data specialization or equivalent experience. Minimum 5 years relevant experience. Advanced knowledge of pharmacometrics, quantitative pharmacology, statistical modeling, and computational science. Demonstrated expertise in model‑informed drug development (MIDD). Experience developing mechanistic, PK/PD, Bayesian, or machine learning models. Advanced programming skills in Python and/or R. Ability to integrate large‑scale biological, clinical, and translational datasets. Demonstrated scientific leadership and independent research capability. Ability to communicate complex quantitative concepts to scientific and non‑scientific audiences. Experience managing multiple concurrent research projects. Preferred Qualifications Master's degree in Computer / Computational / Data Science, or Domain Sciences with computer / computational / data specialization preferred. Postdoctoral or industry experience in quantitative drug development.

QSP, AI/ML.

Pharmacogenomics, Toxicokinetics. Clinical trial simulation, Infectious disease modeling. TB experience, Regulatory interactions. Grant writing experience. #J-18808-Ljbffr University of California - San Francisco