Postdoctoral Position in Jeffrey J. Gray's Computational Protein Structure and Design Lab Full-time

Postdoctoral Position in Jeffrey J. Gray's Computational Protein Structure and Design Lab

Are you excited to explore a yet-to-be-solved problem at the heart of AI-based protein engineering? Join Jeffrey Gray's research lab to develop and mature some of the most in-demand research skills in academia and industry today.

New approaches in deep neural networks are revolutionizing the study of protein structure, but so far these advances have not solved the critical issues to be able to design new therapeutic antibodies from scratch. The Gray lab is a leader in the study of protein-protein interactions and computational modeling of antibodies, including emerging deep learning approaches. This position will allow you to learn the emerging deep learning approaches to proteins and antibodies and craft new machine learning approaches for antibody engineering, protein-protein docking, and carbohydrate modeling. We create new methods and collaborate with academics and industry to apply these methods to important biological problems and to therapeutics. You will be a part of a dynamic, collaborative, and inclusive research group.

• Highly competitive salary (up to $80,000 stipend) goes far in affordable Baltimore.
• Full benefits including health insurance (coverage for eye and dental insurance).
• The Gray laboratory is part of the Rosetta Commons (Prof. Gray serves as Director), and so you will be able to participate in Rosetta Conferences, workshops, and outreach.
• Johns Hopkins offers an unmatched environment for life sciences research, with a dynamic community in biomolecular engineering, biophysics, biochemistry, and medicine.
• Lab alumni have advanced to positions in industry giants (Genentech, Merck, Pfizer, GSK), and successful recent startups (Generate Bio, Outpace Bio).
• Initial appointment period of one year, with expectation of 2-4 years total.
• State-of-the-art computing infrastructure (NVIDIA H100 and A100 GPUs and CPUs for seamless computing).
• Supportive mentoring environment, with regular 1:1 meetings and Individual Development Plans every 6 months.

Key responsibilities could include, but are not limited to, assisting in the following:

• Review literature on biomolecular structure and design technologies and deep learning approaches.
• Assess gaps in current tools.
• Assess of emerging deep learning methods for application in biomolecular engineering.
• Create of novel deep learning tools for biomolecular engineering, including assembling novel data sets, building new architectures, training and assessing models.
• Critically assess of biomolecular designs using multiple deep learning tools, physics-based models, and structural analysis.
• Plan collaboration with experimentalists, to best assess competing design strategies.
• Write journal articles and presentations for sharing the outcomes.

Qualifications

• PhD in Engineering, biophysics, computational biology, or related field
• Experience with scientific algorithm development, protein biophysics or engineering, protein structure prediction and design.
• Experience in solving complex scientific or engineering problems
• Excellent writing and communication skills
• Ability to work in teams and contribute to a supportive and collaborative work culture