Principal Data Scientist – AI/ML and Optimization

About the role

J&J Innovative Medicine's Data, Data Science and AI global development team is recruiting a Principal Data Scientist focused on AI/ML and optimization. The role builds computational pipelines supporting global clinical operations, including enrollment forecasting, cost estimation and optimization, and country/site selection. The primary location is Madrid, Spain, with other listed locations considered if approved by the business.

Key responsibilities

• Conceive, develop and implement ML, multi-objective optimization and GenAI solutions for clinical trial operations.
• Use operational, real-world and cost data to build ML models and optimization engines for operational planning decisions.
• Develop predictive ML models for time-series outcomes and KPIs, and formulate and solve optimization problems balancing cost, timelines, patient burden, quality and efficiency.
• Integrate predictive modeling with optimization to evaluate operational scenarios and recommend strategies.
• Build explainable decision-support systems and adapt large language models for protocol comparison, data harmonization, schedule optimization and eligibility evaluation.
• Run stochastic enrollment simulations to forecast operational and patient journey outcomes.
• Communicate technical methods and results clearly to diverse audiences and coach junior colleagues.

Required profile

• Ph.D. in a quantitative discipline (computer science, electrical and computer engineering, biostatistics, health economics, biomedical informatics, applied mathematics or similar).
• 5+ years of industry experience delivering data science projects with ML predictive modeling, multi-objective optimization, NLP and GenAI.
• Experience with multi-modal ML, stochastic simulations for time-series forecasting, and multi-objective optimization engines using evolutionary algorithms, reinforcement learning or mixed-integer linear programming.
• Experience with GenAI and clinical LLMs for document parsing and clinical concept disambiguation and harmonization.
• Familiarity with clinical operational data, real-world data, electronic health records, claims and financial data.

Required skills

• MLOps tools (MLflow, Kedro), Git, CI/CD stacks (Jenkins, GitLab) and DevOps tools.
• Python and SQL.
• Python LLM tools (DSPy, LangChain), optimization tools (pymoo) and ML tools (Scikit-learn, XGBoost, Optuna, PyMC).
• Preferred: prior healthcare, MedTech or pharma data science experience, and hands-on use of clinical trial protocols, registries, CTMS, EDC and EHR data.

What we offer

• Base pay range of EUR 61,800 to EUR 106,260.
• Annual bonus, vacation days, parental leave of at least 12 weeks, bereavement and caregiver leave, well-being reimbursement and health programs.
• Service anniversary and recognition awards, and insurance plans for eligible employees and dependents.