Computational Protein Engineer

AeroVironment•Bath Township, OH

1d•Onsite

About The Position

The Biological Materials and Processing Research Team is seeking a Computational Protein Engineer to lead the design and optimization of proteins for use in novel metal separation technologies that address the nation’s growing need for critical materials. This role will focus on de novo protein design and optimizing protein performance and will involve using generative protein design software, machine learning methodologies for analysis of large experimental datasets, and other computational workflows. The successful candidate will play a foundational role in a growing research program and will have the opportunity for significant project ownership. They will join a group of collaborative scientists with diverse skill sets and should have strong communication skills, a collaborative mindset, and an enthusiasm for innovative research.

Requirements

Ph.D. in Computational Chemistry, Biophysics, Protein Engineering, or a related field. (Candidates with an M.S. and 5+ years of specialized experience will be considered).
Extensive experience with the use of regression, optimization, protein language, or transformer models to analyze large datasets.
Experience using generative and physics-based models for de-novo protein design and in-silico screening.
Strong understanding of protein structure-function relationships.
Fluency in Python and/or C++/Rust for pipeline development and custom script generation.
Experience automating computational workflows and implementing them on high-performance computers to reduce design turnaround time.
U.S. Citizenship is required due to government facility access requirements.

Nice To Haves

Experience coordinating work done by third parties (e.g. CROs, academic collaborators, and other external partners).
Familiarity with the structure and function of metalloproteins.
Experience with quantum mechanical modeling of protein-metal interactions
Experience with (or willingness to learn) theory behind experimental techniques for characterizing protein function.

Responsibilities

Machine Learning for Data Analysis: Implement and fine-tune machine learning algorithms to analyze large protein function datasets and generate sequences with predicted improvements in performance.
Computational Design & Generative AI: Deploy advanced protein design suites (e.g., RFDiffusion, Rosetta, LigandMPNN) to architect novel binding pockets for polyvalent metals.
Structural Bioinformatics: Develop and implement high-throughput workflows for in-silico assessment of the quality of engineered protein scaffolds.
Interdisciplinary Interface: Translate computational predictions into actionable design parameters and assess resulting experimental data in collaboration with experimental team members as a part of design-test-learn workflows.