Understanding biological structure central to deciphering the mechanisms of life and advancing drug design. We are developing next-generation, structure-centric, multimodal foundation models that power key applications—from complex structure prediction and functional modeling to de novo molecular design.
We are a cross-disciplinary team of experts in machine learning, structural biology, computational chemistry, and bioinformatics, supported by strong engineering infrastructure and access to large-scale compute resources. We aim to develop open, high-precision, generalizable models that drive breakthroughs in biology and drug discovery.
Responsibilities:
1) Collaborate closely with a multidisciplinary team of ML researchers, computational biologists, and chemists to tackle cutting-edge scientific challenges in molecular modeling.
2) Contribute to the design, training, and optimization of large-scale models for structure prediction across diverse biomolecular systems, addressing key challenges such as conformational sampling, binding affinity estimation, and de novo molecular generation.
3) Translate insights from structural biology, experimental data, and physical principles into scalable model architectures and generative algorithms.
What We Offer
1) A collaborative, impact-driven environment at the intersection of biology and AI.
2) Access to cutting-edge compute infrastructure and proprietary tools.
3) Opportunities to contribute to open science and transformative technologies in drug discovery.
Minimum Qualifications:
1) PhD in Computational Biology, Structural Biology, Computer-Aided Drug Design (CADD), Biophysics, or a related field, with publications in top-tier journals or contributions to widely adopted tools.
2) 1~5 years of industry or postdoctoral experience with a proven track record of applying computational tools in drug discovery or molecular biology.
3) Extensive experience with computational tools and workflows in structural or computational biology, including molecular dynamics (e.g., GROMACS, AMBER), docking (e.g., AutoDock, Glide), quantum chemistry (e.g., ORCA, Gaussian), structure prediction and design (e.g., Rosetta, RFDiffusion), or analysis of cryo-EM/X-ray data.
4) Hands-on experience integrating wet-lab and computational data, and applying structural or biological insights to address complex biological problems. Proficiency in programming and scientific computing (e.g., Python, C++, bioinformatics pipelines).2
5) Strong scientific curiosity, a collaborative mindset, and the ability to quickly learn new concepts and tools.
Read Full Description