Principal Scientist, Computational Protein Design

The Role

Moderna’s Therapeutics Research group is seeking a talented, experienced, and highly motivated Principal Scientist to support computational protein design across therapeutic research. This role will focus primarily on the design and optimization of T cell receptors and antibodies, while also contributing to broader protein design efforts across a range of therapeutic modalities.

The successful candidate will bring deep expertise in protein structure, de novo binder design, molecular recognition, and state-of-the-art computational design methods and workflows. They will serve as a scientific and technical leader for computational binder design, helping to build a next-generation platform for the discovery, engineering, and optimization of TCRs and antibodies against defined targets. This individual will work in close partnership with structural biology, directed evolution, immunology, translational science, and program teams to advance platform innovation and therapeutic programs across Moderna’s Research and Early Development portfolio.

• Lead and execute computational protein design campaigns across therapeutic research, with a focus on de novo binder design for TCRs and antibodies.
• Drive computational binder optimization approaches to improve affinity, specificity, stability, expression, cognate pairing efficiency, potency, develop ability, sequence liabilities, and compatibility with mRNA-expressed therapeutic formats.
• Help build an integrated computational-to-experimental design platform that connects generative design, docking, interface scoring, rational library design, display or functional screening, next-generation sequencing, and active-learning cycles.
• Establish computational off-target screening strategies for engineered TCRs and other binders, including structural motif scanning, alloreactivity risk assessment, counter selection logic, and prioritization of candidates for experimental validation.
• Partner with cross-reactivity, microbial display, directed evolution, structural biology, functional assay, and program teams to convert model outputs into experimental data and incorporate assay results into iterative model improvement.
• Evaluate, deploy, and advance state-of-the-art computational methods, including structure prediction, inverse folding, diffusion- or flow-based generation, protein language models, molecular docking, molecular dynamics, interface scoring, and multi-objective optimization.
• Identify external technologies, datasets, software capabilities, and strategic partnerships that accelerate computational protein design workflows.
• Monitor emerging literature and apply leading-edge methods in machine learning, predictive modeling, and protein engineering.
• Extend protein design capabilities beyond binders where strategically valuable, including enzymes or catalytic scaffolds, DNA- or RNA-binding proteins, protein switches, engineered scaffolds, and other functional domains relevant to therapeutic platform concepts.

• PhD in computational biology, protein engineering, bioinformatics, structural biology, biophysics, or a closely related discipline.
• At least 5 years of post-graduate experience in computational protein design, with a demonstrated track record in de novo binder generation and optimization using AI/ML-guided and structure-informed design approaches.
• Demonstrated experience connecting computational design strategies to experimental validation and optimization workflows.
• Experience leading or contributing to discovery programs that require alignment across computational biology, AI/ML, data engineering, structural biology, immunology, translational science, preclinical development, external partners, and senior scientific stakeholders.
• Strong publication record or equivalent record of scientific impact in computational protein design, structural biology, protein engineering, or a related field.
• Technical fluency with modern computational protein design and structural modeling tools, such as Alpha Fold, Alpha Fold-Multimer, Rosetta, PyRosetta, RF diffusion, ProteinMPNN, and related models.
• Experience…