2027 Future Talent Program – Translational Sciences and Outsourcing – Co-op

MSD • Boston, MA

4d • $39,108 - $111,111 • Hybrid

About The Position

The Future Talent Program offers cooperative education opportunities lasting up to six months and involving one or more projects. This opportunity is in the Research and Development Division. The co-op will join the Translational Sciences and Outsourcing (TSO) team within the Pharmacokinetics, Dynamics, Metabolism, and Bioanalytics (PDMB) department and contribute to an AI-enabled translational modeling project predicting exposure across dose levels in preclinical species. The work combines data curation, machine learning, model benchmarking, and scientific communication to predict toxicokinetics (TK) in support of drug metabolism and pharmacokinetics (DMPK) and nonclinical drug safety (NDS) decisions when only limited initial in vivo data are available.

Working with Data Science, PKPD, DMPK, preclinical toxicology, and related scientists, the co-op will apply AI/ML methods to pharmaceutical PK/TK data relevant to preclinical study design and therapeutic-window assessment. The project will develop and benchmark structure-aware models combining compound structures, physicochemical properties, and initial in vivo PK/TK data to predict exposure at untested dose levels using public and internal data. It will assess whether AI, ML, and mechanistic hybrid approaches improve prediction accuracy, uncertainty estimation, and detection of nonlinear exposure compared with standard empirical and mechanistic baselines.

The co-op will produce a curated cross-dose preclinical PK/TK dataset with provenance, quality checks, and holdout splits; a documented benchmark comparing AI-enabled and hybrid models with empirical and mechanistic baselines; a report describing where these approaches add value and where they do not; and a final presentation of objectives, methods, results, limitations, and recommendations. Project outcomes may also be shared through internal and/or external presentations and publications. The position offers hands-on experience in molecular representation learning, model benchmarking, uncertainty estimation, PK/TK data analysis, and scientific communication in a cross-functional pharmaceutical R&D environment.

Requirements

• Currently pursuing a Master's or Ph.D. degree in data science, computer science, applied mathematics, statistics, computational chemistry, chemical or biomedical engineering, pharmaceutical sciences, or a related quantitative discipline.
• Research experience in machine learning, statistical modeling, scientific computing, or computational modeling.
• Strong Python programming skills, including scientific computing with NumPy, pandas, and scikit-learn.
• Experience with deep learning frameworks such as PyTorch or JAX.
• A solid foundation in machine learning, statistics, model evaluation, and reproducible analysis workflows.
• Ability to work with messy tabular or time-series scientific data and translate analytical findings into clear plots and written summaries.
• Effective written and verbal communication skills and ability to collaborate in a cross-functional research environment.

Nice To Haves

• Exposure to graph neural networks, molecular representation learning, ChemProp, QSAR modeling, or related cheminformatics methods.
• Familiarity with ODEs, dynamical systems, differentiable simulation, torchdiffeq, Neural ODEs, or mechanistic modeling concepts.
• Background or strong interest in pharmacokinetics, toxicokinetics, pharmacometrics, PBPK, ADME, or preclinical safety assessment.
• Interest in agentic AI or LLM-enabled tooling for scientific workflow automation.
• Fluency in leveraging state-of-the-art AI tools for productivity, such as Claude Code, ChatGPT, Gemini, or DeepSeek.

Responsibilities

• Curate and quality-check preclinical cross-dose PK/TK datasets, documenting provenance and reusable data definitions and establishing appropriate holdout splits.
• Analyze TK exposure endpoints such as AUC and Cmax across compounds, doses, and routes of administration to identify trends, nonlinearities, and data limitations.
• Develop and benchmark AI-enabled and hybrid modeling approaches against baselines such as linear scaling, power/Emax models, QSAR/ChemProp-based methods, and applicable mechanistic approaches.
• Evaluate model performance, uncertainty estimation, and detection of nonlinear PK behavior, including saturation or sex differences.
• Create visualizations, written summaries, and technical presentations for cross-functional stakeholders.
• Share project outcomes through internal and/or external presentations and publications.

What This Job Offers

• Career Level: Intern