Scientist, Protein Design

Moderna is seeking a talented, creative, and motivated Scientist to contribute to the AI-enabled design of de novo antibodies or other binder modalities and de novo design of antigens across discovery programs. This is a hands-on computational protein design role for a scientist who can apply modern generative methods, agentic AI workflows, and structure-based design tools to help create, score, and improve binders and antigens for experimental validation. The Scientist will be part of a highly collaborative, multidisciplinary team working to invent how AI-designed binders can function in vivo as part of mRNA therapeutics, including as stand-alone biologics, targeting modules, and components of next-generation multi-protein systems. The Scientist will work closely with computational designers, data scientists, and experimental teams within Computational Design and In Vitro Selection and across Moderna Research to advance novel mRNA-delivered protein candidates. The ideal candidate will bring strong coding and protein-design skills, curiosity about new AI-enabled design approaches, and the ability to translate experimental feedback into improved designs. This is a unique opportunity to work in an innovative environment at the intersection of AI protein design, de novo binder discovery, and mRNA therapeutics. Here’s What You’ll Do Apply AI-enabled protein design workflows to generate and prioritize de novo antibodies and binder modalities or partial de novo design of antigens for experimental testing. Use structure prediction, generative design, sequence design, docking, scoring, and developability analyses to create binder designs against diverse therapeutic targets. Build, maintain, and improve Python-based workflows for model inference, automated design generation, scoring, filtering, and result visualization under the guidance of senior team members. Partner with experimental colleagues to interpret screening, selection, biophysical, and developability data, and use those data to guide iterative design cycles. Contribute to benchmarking and validation of new computational methods so that promising tools can be incorporated into binder-design campaigns. Explore and prototype agentic AI design workflows that connect target analysis, design generation, scoring, and experimental feedback. Develop biological and structural understanding of assigned targets through literature review, analysis of internal and external data, and discussion with project teams. Collaborate with cross-functional teammates to plan experiments, summarize design rationale, and communicate results in team meetings and written updates. Maintain awareness of advances in generative protein design, agentic AI systems, antibody engineering, and de novo binder discovery. Contribute scientifically and technically to multiple discovery efforts in parallel. Here’s What You’ll Need (Basic Qualifications) PhD in Biophysics, Biochemistry, Structural Biology, Computational Biology, Computer Science, or a related field. Hands-on experience in computational protein design, protein structural modeling, applied machine learning, or a closely related area. Strong Python coding skills and experience building reproducible scientific analysis or design workflows in Linux-based environments. Experience with modern protein structure prediction and design tools, such as RFdiffusion, ProteinMPNN, AlphaFold-family methods, Rosetta, protein language models, or related generative approaches. Ability to analyze protein designs and experimental datasets, identify next design steps, and communicate conclusions clearly to multidisciplinary collaborators. Strong critical-thinking, troubleshooting, and problem-solving skills. Excellent written, presentation, and interpersonal communication skills. Ability to work both independently and collaboratively in a fast-paced, cross-functional research environment. Here’s What You’ll Bring to the Table (Preferred