The Keiser Lab at UCSF is looking for highly motivated postdoctoral candidates with a background in machine learning, molecular dynamics, computational chemistry, or related fields. The candidate would work to integrate deep learning methods with molecular dynamics (MD) simulations. The project involves the design and testing of efficient computational ligand-protein interaction representations for the analysis of MD trajectories using convolutional neural networks.
Python expertise required. PyTorch or Chainer experience preferred. Desired, but not strictly required, skills include experience with pandas and sklearn. Expertise with massive and/or distributed dataset analysis is a plus. MD trajectories will be provided by expert partners and the project will proceed under an established collaboration.
A productive track record with at least one first-author publication is required. We seek a driven individual who will hit the ground running, lead her/his research independently, and communicate frequently and clearly to the field and industry partners.
Just north of Silicon Valley, the lab’s location at UCSF Mission Bay directly adjoins SoMa district and the heart of SF’s tech and artificial intelligence startup scene.
How to apply
Interested candidates should submit a CV and arrange that three letters of reference be sent directly to email@example.com. Please reference “postdoc-dnn-md”.
UCSF is an equal opportunity employer.