Associate Scientist, Postdoctoral Fellow - Pharmacokinetics

Merck•Boston, MA

1d•Hybrid

About The Position

Be a part of the legacy: Postdoctoral Research Fellow Program Our Research Laboratories’ Postdoctoral Research Fellow Program aims to be a best-in-industry program for industrial postdoctoral researchers, designed to provide you with an academic focus in a commercial environment. With the resources, reach, and expertise of a large pharmaceutical company, postdoctoral researchers will be positioned to excel in an institution committed to breakthrough innovation in research and discovery. The Pharmacokinetics, Dynamics, Metabolism, and Bioanalytics (PDMB) function at research laboratories is seeking a highly motivated postdoctoral fellow with expertise in machine learning to help transform drug discovery and preclinical development. You will join an interdisciplinary team and collaborate closely with research partners across our global organization. You will invent, prototype, and apply advanced Machine Learning (ML) methods—particularly in generative modeling and related areas—to expand our capabilities in designing, prioritizing, and characterizing novel therapeutic candidates.

Requirements

Demonstrated research excellence and problem-solving ability; strong motivation to learn, innovate, and deliver
Proficiency in core ML/statistics topics such as probability, statistical inference, optimization, discrete math/algorithms, and/or probabilistic modeling
Strong programming skills in Python and experience with modern ML frameworks (e.g., PyTorch, TensorFlow)
Track record of publications and/or presentations in ML, computational chemistry/biology, or related fields
Excellent collaboration and communication skills; proven ability to work in cross-functional teams

Nice To Haves

Experience with molecular representations (e.g., SMILES, graphs), generative models (e.g., diffusion models, VAEs, flow models), and sequence/structure models (e.g., transformers, GNNs, protein or RNA models)
Familiarity with cheminformatics/biophysics toolkits (e.g., RDKit), docking or molecular simulation, ADMET modeling, or DMPK-relevant endpoints
Practical experience with experimental design, active learning, uncertainty quantification, or multi-objective optimization
Software engineering best practices (Git, testing, containers), and experience working with large datasets and cloud/GPU environment postdoctoralopportunities

Responsibilities

Conduct original research to develop state-of-the-art AI/Machine learning methods for drug discovery (e.g., molecular generative models, multi-objective optimization, property prediction, active learning, document authoring, document generation, hybrid AI system, multi-agent system)
Design and execute experiments, analyze results rigorously, and iterate rapidly on model architectures and training strategies
Build robust, reproducible code and workflows; contribute to shared libraries and documentation
Collaborate with chemists, biologists, Pharmacokinetics, Dynamics, Metabolism, and Bioanalytics (PDMB) scientists, and data/ML engineers to translate methods into impactful applications
Communicate findings through internal presentations and peer-reviewed publications; present at conferences and workshops