Protein ML Senior Principal Data Scientist

Sanofi • Waltham, MA

7d • Onsite

About The Position

As a Protein ML Senior Principal Data Scientist on the Vaccines R&D Data and Computational Sciences team, you will design and deploy machine-learning models to predict protein properties and accelerate development of next-generation vaccines. The work uses protein language models and foundational AI to predict immunogenicity, stability, and manufacturability—properties important to developing safe and effective vaccines.

Working at the interface of computational and experimental science, you will collaborate with antigen design and bench lab teams to iteratively refine protein property predictors and translate computational insights into vaccine candidates. The role also contributes to Sanofi’s AI-driven research and global vaccination efforts.

Requirements

• PhD 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.
• Fluent English.
• Strong problem-solving, communication, and collaboration skills across multidisciplinary teams.
• Demonstrated ability to communicate across computational and bench lab teams and adapt messaging to diverse audiences, including senior leadership.
• Proven ability to mentor junior colleagues and lead collaboratively in protein modeling.

Nice To Haves

• Exceptional track record in computational biology, including protein language models, biophysics, and development of AI-based predictive models.
• Prior experience with immunogenicity predictors.
• Advanced proficiency in Python, R, and SQL, with hands-on experience in PyTorch and AI-based structural modeling tools such as AlphaFold, OpenFold, and Boltz.
• Deep knowledge of protein representation models such as ESM.
• Familiarity with molecular dynamics, next-generation sequencing analysis, and deep mutational scanning.
• Familiarity with agentic tools such as Claude Code for automated software engineering is strongly preferred.

Responsibilities

• Develop state-of-the-art protein property prediction models, focusing on immunogenicity, stability, and manufacturability, to support vaccine design.
• Leverage and refine language-based foundational protein representations to accelerate identification and optimization of vaccine candidates.
• Analyze relationships between protein sequences, structures, and functional data to uncover generalizable representations applicable across vaccine programs.
• Collaborate with structural biology, protein design, and bench lab teams to shape protein-modeling strategy and iteratively improve model quality.
• Maintain the modeling codebase using best coding practices and ensure results are robust, reproducible, and well-documented.
• Mentor and upskill colleagues on advances in protein-modeling tools and techniques, fostering continuous learning and scientific rigor.
• Communicate scientific findings clearly to internal and external stakeholders, adapting detail to the audience.

Benefits

• Health and wellbeing benefits, including high-quality healthcare, prevention, and wellness programs.
• At least 14 weeks of gender-neutral parental leave.
• Mentoring and international mobility programs.
• Opportunities to grow across four continents.
• Employees may be eligible to participate in company employee benefit programs.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree