Postdoctoral Researcher - Biomolecular AI & Protein-Ligand / Protein-membrane interaction modeling

At Microsoft Research AI for Science we seek highly motivated Postdoctoral Researchers on all-atom molecular dynamics for protein-ligand and/or protein-membrane interactions.  Microsoft Research AI for Science focuses on the development of machine learning and artificial intelligence methods for transforming molecular simulation and discovery of novel materials, drugs and chemical reactions. The BioEmu project aims to model the dynamics and function of proteins, how they change shape, bind to each other, and bind small molecules. This approach will help us to understand biological function and dysfunction on a structural level and lead to more effective and targeted drug discovery. Our BioEmu-1 model was published in Science (see our blog post for links to our open-source software and other resources and this explainer video ).  The current role focuses on very large-scale  data generation for protein-ligand and/or protein-membrane interactions using molecular dynamics (MD) simulations and free energy calculations. These data will be used for training and validating new versions of BioEmu. This role emphasizes scientific ownership, cross-disciplinary collaboration, and scalable systems thinking, moving beyond one-off experiments or models to build reusable, high-impact data and modeling pipelines.   Why this role is exciting   You’ll be running very large-scale data generation campaigns to train next-generation AI methods that can make a meaningfully impact on move how biomolecular modeling is done and improve success rates in drug design discovery forward . You provide your expertise on the technical and the design level, making decisions about and creating datasets that have crucial impact on our AI models. It’s an opportunity to bridge state‑of‑the‑art ML with meaningful biomedical impact in a highly collaborative research environment .

Design, execute, and analyze large-scale molecular dynamics (MD) simulations, including protein-ligand, protein-membrane, and free energy perturbation (FEP) studies. Develop high-quality, machine learning-ready datasets by translating scientific questions into scalable data generation campaigns and defining appropriate quality standards and evaluation metrics. Build reproducible computational workflows and automation pipelines using Python and distributed computing infrastructure. Collaborate with machine learning researchers, computational biologists, and research engineers to integrate simulation outputs with advanced modeling workflows. Design and implement model-informed experimentation strategies that leverage simulation results to improve biological modeling and predictive performance. Validate computational findings against reference calculations and experimental data, assessing convergence, uncertainty, and methodological limitations while troubleshooting technical challenges independently. Drive research projects from ambiguous scientific questions to impactful outcomes, contributing novel methods, publications, datasets, software, and broader research direction Qualifications Required Qualifications PhD (or equivalent experience) in Computational Biology, Structural Biology, Biophysics, Physics, Statistical Mechanics, or a related field. Expertise in biomolecular simulation, including molecular dynamics system setup, force field selection, simulation parameterization, and related methodologies. Deep theoretical and practical experience with free energy perturbation (FEP), alchemical free energy methods, and assessment of convergence, uncertainty, and simulation quality. Experience developing scientific software and computational workflows in Python Demonstrated ability to lead research projects independently and collaborate effectively across multidisciplinary teams. Perferred Qualifications Experience with membrane modeling, including lipid composition selection, equilibration, and simulation setup Experience integrating structural