Computational and Experimental Scientist

About the Role

Join a lean team at an early-stage biotech company developing AI tools for peptide and protein design. You will connect computational design, experimental validation, and platform operations, closing the loop from sequence generation to kinetics data and model improvements.

What You'll Do

• Improve discrete diffusion and folding models for peptide and protein design, including model architecture and reasoning capabilities.
• Operate an inference platform at scale and analyze usage patterns, including signups, churn, and customer segments.
• Write, debug, and maintain production protocols for liquid-handling robots and plate automation.
• Design and run BLI and SPR assays, fit kinetic curves, perform quality control, and diagnose assay failure modes.
• Manage screening instruments and write precise protocols for external laboratory partners.
• Use receptor biology, structure, and scoring to evaluate designs and make platform outputs useful to scientists.
• Iterate on designed sequences using experimental kinetics data to improve models and subsequent designs.

What We're Looking For

• Typically 3 to 11 years of relevant experience, including hands-on wet-lab work and experience across biology, bioinformatics, and machine learning.
• Experience building or operating protein or biological models, such as discrete diffusion models, protein language models, or structure prediction systems, in a design-make-test workflow.
• Practical experience with tools such as ESM or ProtT5 and sequence design methods such as RFdiffusion or BindCraft.
• Hands-on proficiency writing and debugging methods for Hamilton, Tecan, Opentrons, or equivalent liquid-handling platforms.
• Experience independently designing BLI or SPR assays, fitting kinetic curves, extracting binding parameters, and diagnosing assay artifacts.
• Python or equivalent scripting skills for automation and kinetic data analysis, plus an understanding of protein structure, receptor biology, and scoring.
• Ability to troubleshoot instruments and protocols quickly, operate inference systems or refine model architectures, and explain scientific workflows clearly.
• Experience in biotech or scientific software customer-facing roles, including user conversion, customer success, or solutions engineering, is relevant. Familiarity with scientific platform usage and customer buying processes is also valuable.