Machine Learning Scientist - Diffuse - Remote

Overview

The Diffuse Project is dedicated to advancing our understanding of protein motion through the use of diffuse scattering – a signal in X-ray crystallography that is currently under-utilized or ignored, that will unlock our ability to measure protein dynamics. We are bringing together a diverse team of researchers, software developers, and beamline scientists to accomplish our mission. We are committed to Open Science principles of making all of our work, software, and data open and FAIR all along the way.

In Short

• Seeking a Machine Learning Scientist for the Diffuse Project.
• Focus on developing machine learning methods for structural biology data.
• Expertise in generative modeling, reinforcement learning, or representation learning is desired.
• Design, train, and deploy ML models from experimental X-ray crystallography data.
• Collaborate with domain scientists to integrate outputs with experimental pipelines.
• Strong background in linear algebra, statistics, and deep learning architectures required.
• Familiarity with structural biology or protein dynamics is advantageous.
• MS or PhD in relevant fields with at least two years of experience.
• Remote position with some travel for collaboration.
• Competitive compensation based on experience and location.

Requirements

• Strong background in linear algebra, statistics, probability theory, optimization methods, and deep learning architectures.
• Hands-on experience with generative models, representation learning, or reinforcement learning.
• Proven ability to build and debug large-scale ML algorithms.
• Familiarity with structural biology, protein dynamics, or physics-based modeling.
• Ability to work effectively in a multidisciplinary team environment.
• Familiarity with Pytorch.

Benefits

• Competitive compensation package.
• Opportunity to work on cutting-edge research in structural biology.
• Flexible remote working environment.
• Collaborative interdisciplinary team.
• Engagement in Open Science principles.