Future Talent Program Intern - Translational Sciences and Outsourcing (Data Science)

About the role

The 2027 Future Talent Program offers internships of up to 12 weeks, each including one or more projects, within Merck's Research and Development Division. This internship is in the Translational Sciences and Outsourcing (TSO) Data Science team of the Pharmacokinetics, Dynamics, Metabolism, and Bioanalytics (PDMB) department. The intern benchmarks AI/ML methods for pharmacokinetic curve prediction, working with scientists to support decisions across drug discovery and development.

Key responsibilities

• Analyze large-scale pharmacokinetic and molecular datasets and prepare them for reproducible modeling and evaluation.
• Implement and benchmark classical machine learning baselines, molecular-structure-based models, and representative time-series or mechanism-informed approaches for pharmacokinetic curve prediction.
• Design and compare random, scaffold, time-based and chemical-similarity-aware evaluation settings, quantifying performance across compound novelty levels to identify data leakage and limits of prospective generalization.
• Collaborate with scientists to interpret results and ensure benchmark conclusions are scientifically meaningful.
• Document methods and results and contribute to a draft manuscript or technical report.
• Present project outcomes at the end-of-summer intern symposium.

Required profile

• PhD student in computational chemistry, cheminformatics, machine learning, computer science, computational biology, statistics or a related field.
• Strong publication record in top-tier peer-reviewed journals or ML conferences (e.g. ICML, ICLR, NeurIPS).
• Interest in applying modern AI/ML to large-scale pharmaceutical data and in reproducible, publication-oriented research.

Required skills

• Strong Python programming, with machine learning or deep learning frameworks such as PyTorch.
• Ability to build reproducible analysis pipelines and understand how data leakage and evaluation design affect model generalization.
• Experience designing comparative studies and communicating technical results clearly.
• Preferred: pharmacokinetics, ADMET, cheminformatics tools (SMILES, fingerprints, RDKit, Chemprop, Uni-Mol), molecular similarity analysis, time-series modeling, and neural ODEs.

Expected deliverables

• A reproducible evaluation workflow with documented datasets, splits, model configurations, metrics and visualizations.
• A final presentation of objectives, methods, results, conclusions and recommendations.
• A draft manuscript prepared with the project team and subject to internal publication review.

Salary range: $39,108 through $111,111. The position may close before the posted end date.