Senior Scientist I, Computational Protein Design

Generate Biomedicines•Somerville, MA

7d•$172,000 - $241,000•Hybrid

About The Position

Generate Biomedicines is seeking a creative, rigorous scientist to develop computational technologies and lead applied platform research that expand the capabilities of protein therapeutics. The role develops reusable methods, scoring and evaluation tools, model benchmarks, agentic systems, and scientific workflows for protein design, engineering, and optimization, spanning the creation of new proteins, modification of existing molecules, and integration of molecular components for new therapeutic applications. This position combines technology development with applied platform research. The scientist identifies recurring scientific needs, leads research, and turns successful approaches into durable capabilities with clear interfaces and validated performance. In partnership with program teams, biologists, and experimental scientists, the role tests and refines capabilities in relevant biological settings, establishes proof of concept for new molecular properties and functions, and combines validated approaches to enable therapeutic applications and pipeline programs. The scientist leads computational research to establish feasibility, resolve technical risks, and make successful approaches reusable across targets and programs. The role is based in Generate's Somerville, Massachusetts office, with flexibility for hybrid work. Compensation includes a base salary range of $172,000–$241,000 per year, eligibility for an annual bonus, equity compensation, and a competitive benefits package.

Requirements

Strong scientific and quantitative foundations, with practical fluency in modern machine learning and computational methods relevant to protein science, molecular modeling, or biological design.
A record of translating research ideas into reusable computational methods, models, software, or workflows and demonstrating their value on biological problems.
Experience designing rigorous benchmarks or evaluation frameworks, including dataset construction, baselines, metric validation, uncertainty, confounding, and failure analysis.
Experience addressing applied biological or therapeutic problems with teams of machine learning researchers, engineers, protein scientists, biologists, and experimental scientists, including framing hypotheses, defining informative studies, and using results to guide decisions.
Strong hands-on computational skills, including Python, modern machine learning frameworks such as PyTorch or JAX, and experience contributing reliable code in a shared environment.
Strong understanding of protein structure, sequence–structure–function relationships, molecular interactions, and biophysics, with the ability to reason critically about computational predictions and experimental evidence.
A PhD in a relevant scientific or engineering discipline.
At least three years of industry experience following completion of the PhD.
Demonstrated ability to lead consequential technical work with substantial independence.

Nice To Haves

Experience building LLM-enabled agents, scientific copilots, or multi-agent systems for therapeutic design or scientific hypothesis generation and testing, including tool use, planning, evaluation loops, human oversight, and assessment of reliability.
Relevant experience in protein or antibody engineering, molecular modeling, structure-guided optimization, generative design, or related approaches.
Background in computational protein design or engineering, computational biology, machine learning, biophysics, or adjacent quantitative disciplines.

Responsibilities

Lead technology development and applied platform research by identifying high-value capability gaps and molecular or biological challenges, formulating testable hypotheses, and defining research plans, milestones, and decision criteria.
Drive projects from scientific question through computational implementation and experimental proof of concept to validated, reusable capabilities.
Develop computational methods for protein design, optimization, and interaction modeling using generative, predictive, and biophysical approaches.
Create scores and benchmarks to assess sequences, structures, biological functions, and developability; define intended uses, interfaces, assumptions, and success criteria across targets, molecular formats, and therapeutic applications.
Build reproducible datasets and evaluation protocols that reveal strengths and failure modes, quantify uncertainty, and guide appropriate use.
Partner with assay, structural, and experimental scientists to design informative molecular libraries and iterative design–build–test–learn studies.
Demonstrate control of properties such as binding specificity, conditional activity, molecular assembly, stability, or developability; analyze experimental readouts, diagnose failures, and use results to improve methods and establish where they generalize.
Partner with machine learning and engineering teams to translate platform and application needs into model objectives, evaluation criteria, and data requirements; stress-test new models and help turn successful research into reliable, maintainable software.
Develop agentic systems and multi-agent workflows that connect scientific information, generative and predictive models, internal data, analysis tools, and experimental results to formulate hypotheses, propose designs, evaluate evidence, and recommend informative next steps.
Establish mechanisms for human oversight, traceability, and rigorous measurement of agentic system reliability.
Work with application teams to combine validated capabilities to address consequential molecular or biological challenges, establish technical feasibility in therapeutically relevant settings, assess performance against appropriate references, and test potential use across targets or programs.
Generate evidence to inform advancement or discontinuation, target selection, and nomination of differentiated therapeutic programs.
Turn research outcomes into documented methods and reference workflows, support adoption by application and program teams, and translate lessons across projects into broader platform improvements.