The Astera Institute's diffUSE Project is hiring a Scientist to build machine learning algorithms that extract protein conformational dynamics directly from experimental structural biology data. You'll develop novel generative models that treat experimental observables like electron density and diffraction patterns as direct training inputs, advancing the fitting of dynamic structural biology models.
What You'll Do
- Develop and own novel algorithmic approaches to extracting protein dynamics from experimental observables.
- Design, train, and deploy open-source ML models that learn directly from experimental X-ray crystallography data for conformational ensemble modeling.
- Develop and benchmark metrics for conformational ensemble modeling and comparison against experimental data.
- Collaborate with domain scientists to integrate outputs with experimental pipelines and refine hypotheses in an iterative design–test–learn loop.
What We're Looking For
- PhD in Data Science, Computer Science, Bioinformatics, Biophysics, Computational Chemistry, or a related field.
- Deep experience with generative models, probabilistic inference, and/or representation learning.
- Ability to work effectively in a multidisciplinary team environment.
- Experience with probabilistic/Bayesian methods.
- Inverse problems experience.
Team & Environment
This is a full-time position within the diffUSE Project, in-person at Radial, a division of the Astera Institute. Projects operate like high-velocity startups with a focus on ambitious goals, matching structure to the problem, and attracting strong technical talent.
Benefits & Compensation
- Competitive compensation package, commensurate with experience and location. Posted range is based on the Bay Area.
Work Mode
This is an onsite position located in the Bay Area.
