Scientist I, Computational Protein Design

Generate Biomedicines•Somerville, MA

6d•Hybrid

About The Position

Generate Biomedicines is seeking an inventive Computational Protein Design Scientist to work at the intersection of computational protein design, machine learning, and experimental biology. The role uses computational expertise and biochemical understanding to guide protein-design strategy for therapeutic programs while developing reusable design capabilities. It works closely with machine learning and experimental platform teams to integrate AI-designed proteins with experimental data. The scientist will translate therapeutic hypotheses into design and data-generation plans, execute protein-design campaigns, interpret results, and inform decisions within cross-functional teams. The role also applies lessons from programs to improve design methods, workflows, and scientific requirements, making program execution more efficient, reproducible, and scalable. The position is based in the Somerville, Massachusetts office, with flexibility for hybrid work. Compensation is a base salary of $140,000–$196,000 per year, with eligibility for an annual bonus, equity compensation, and a competitive benefits package.

Requirements

PhD in protein engineering, biochemistry, bioengineering, molecular biology, computational biology, bioinformatics, or a related field.
Demonstrated experience formulating protein-design strategy in areas such as de novo protein design, protein optimization, protein engineering, antibody engineering, or related molecular-design problems.
Strong practical understanding of protein sequence, structure, and their relationship to molecular properties and biological function.
Experience with experimental design and interpreting complex biological datasets to guide protein-design decisions.
Working proficiency in Python and ability to develop reproducible analyses and computational workflows.
Strong scientific judgment and creativity, with the ability to propose and act on decisions with incomplete information.
Ability to clearly communicate technical concepts, assumptions, risks, and tradeoffs to cross-functional audiences.

Nice To Haves

Experience with machine learning, statistical modeling, developing AI-agent workflows, workflow orchestration, or programmatic interfaces; these skills can also be developed in the role.

Responsibilities

Translate therapeutic hypotheses and program needs into end-to-end protein-design campaigns, data strategies, and technical milestones, identifying and navigating key uncertainties.
Identify recurring capability gaps, successful approaches, and failure modes, and translate these insights into improved methods, workflows, and priorities.
Connect computational model development with experimental validation, sharing biological and computational learnings between collaborators.
Use biochemical knowledge to shape informative experiments, accounting for complex assay readouts, signal and noise properties, and experimental-design tradeoffs.
Contribute to workflows that connect scientific information, protein-design models, data, and tools; apply these workflows to program questions and design decisions and evaluate their outputs and reliability.
Develop and communicate data-driven design recommendations that connect molecular observations to program context and next-step decisions.
Document assumptions, results, and limitations so the work is understandable and reusable.