Postdoc: Deep-Learning for Protein Representations & Pipelines

The Rector & Visitors of the University of Virginia; Charlottesville (VA); On-site; USD 52,000 - 64,000; Full time

Job summary

The University of Virginia invites applications for a Postdoctoral Research Associate to develop a deep learning pipeline for benchmarking protein representations and surfaces. The successful candidate will join Dr.

Camille Bilodeau's Chemical Engineering group to lead ML methods using simulations and to build software pipelines interfacing ML models with transport models. Responsibilities include developing Python/PyTorch pipelines, conducting large-scale simulations, creating open-source

Qualifications

• Ph.D. by start date in a related field.
• Experience with deep learning and machine learning methods.

Responsibilities

• Develop a Python-based pipeline to generate ML inputs from protein data.
• Build a PyTorch-based pipeline to predict protein properties from representations.
• Perform large-scale molecular simulations for training data.
• Create an open-source Python package to integrate pretrained models with transport models.
• Lead meetings, report progress to collaborators.
• Publish findings and present at conferences.
• Mentor students and foster an inclusive research environment.
• Contribute to proposal development and new funding opportunities.

Skills

Deep learning

Molecular simulations

Biophysics of proteins

Python-based coding/software

Education

Ph.D. in chemical engineering, biomedical engineering, computer science, or related field

Job description

The University of Virginia invites applications for a Postdoctoral Research Associate to develop a deep learning pipeline for benchmarking protein representations and surfaces. The successful candidate will join Dr.

Camille Bilodeau's Chemical Engineering group to lead ML methods using simulations and to build software pipelines interfacing ML models with transport models. Responsibilities include developing Python/PyTorch pipelines, conducting large-scale simulations, creating open-source