Protein ML Senior Principal Data Scientist

What you'll do

• Develop machine learning models to predict protein immunogenicity, stability, and manufacturability for vaccine design.
• Refine language-based foundational protein representations to accelerate the identification and optimization of vaccine candidates.
• Analyze relationships between protein sequences, structures, and functional data to uncover generalizable representations.
• Collaborate with structural biology and bench lab teams to iteratively improve protein modeling strategies and model quality.
• Maintain the modeling codebase using best coding practices to ensure robust, reproducible, and well-documented results.
• Mentor and upskill colleagues on the latest advances in protein modeling tools and techniques.
• Communicate scientific findings clearly to internal and external stakeholders across various levels of technical expertise.

What we're looking for

• PhD degree in Computational Biology, Data Science, Applied Mathematics, Biophysics, or a closely related field.
• At least 2 years of experience in an industry or academic setting.
• Exceptional track record in computational biology, protein language models, biophysics, and AI-based predictive models (preferred).
• Advanced proficiency in Python, R, and SQL with hands-on experience in PyTorch and tools like AlphaFold, OpenFold, and Boltz (preferred).
• Deep knowledge of protein representation models such as ESM (preferred).
• Familiarity with molecular dynamics, next-generation sequencing analysis, and deep mutational scanning (preferred).
• Familiarity with agentic tools such as Claude Code for automated software engineering (preferred).
• Fluent English language skills.