Bethel Lab @ UCSD

Open positions

Postdoctoral Scholar – Deep Learning for Protein Design

The Bethel Lab at the University of California San Diego is seeking an outstanding and highly motivated Postdoctoral Scholar to develop and apply deep-learning methods for protein design. Our research combines machine learning, physics-based simulation, structural biology, and experimental protein engineering to understand and design proteins with new structures, dynamics, and functions.

The successful candidate will develop next-generation computational approaches for generative protein design, with an emphasis on using deep learning to design proteins that recognize specific molecular targets, adopt defined conformational states, or exhibit novel biochemical functions. Projects may involve protein language models, diffusion-based generative models, structure prediction, inverse folding, molecular dynamics simulations, and integration of computational design with experimental validation.

Research Directions

Potential projects include:

  • 1. Developing generative deep-learning models for de novo protein design.
  •  
  • 2. Designing proteins that recognize small molecules, lipids, peptides, or protein targets.
  •  
  • 3. Developing machine-learning approaches that explicitly incorporate protein dynamics and conformational ensembles into protein design.
  •  
  • 4. Integrating protein language models with physics-based simulation.
  •  
  • 5. Developing methods to improve the ability of generative models to design proteins at challenging interfaces, including protein–membrane and protein–ligand interfaces.

 

The postdoctoral researcher will have substantial flexibility to develop an independent research direction while collaborating closely with computational scientists and experimentalists in the laboratory.

Qualifications

Applicants should have a Ph.D. or equivalent degree in computer science, computational biology, bioinformatics, or a related field.

Candidates should have demonstrated experience in one or more of the following areas:

  • 1. Generative modeling
  •  
  • 2. Protein structure prediction or protein design
  •  
  • 3. Protein language models
  •  
  • 4. Scientific computing and Python/PyTorch
  •  
  • 5. Strong candidates from adjacent fields—including machine learning, computer vision, generative modeling, or applied mathematics—who are interested in applying their expertise to protein design are particularly encouraged to apply.
  •  

Experience with experimental protein characterization is not required, although an interest in connecting computational predictions with experimental measurements is highly desirable.

What We Offer

The successful candidate will join an interdisciplinary and collaborative research environment at UC San Diego with opportunities to work at the interface of artificial intelligence, protein biophysics, structural biology, and protein engineering. The lab provides access to extensive computational resources as well as experimental infrastructure for protein expression, biochemical characterization, structural biology, and biophysical measurements.

The postdoctoral researcher will have opportunities to:

  • 1. Lead projects toward high-impact publications.
  •  
  • 2. Develop new computational methods and open-source software.
  •  
  • 3. Collaborate with experimental and computational researchers across UC San Diego.
  •  
  • 4. Present research at national and international conferences.
  •  
  • 5. Develop an independent research program and prepare for an academic or research career.
  •  

How to Apply

Please submit:

  • 1. A CV
  •  
  • 2. A brief statement of research interests describing your background and potential research directions
  •  
  • 3. Contact information for three references
  •  

Applications will be reviewed on a rolling basis until the position is filled.

We strongly encourage applications from candidates with diverse scientific backgrounds and from individuals who are excited about developing new approaches at the intersection of AI and molecular science.