(Associate) Scientist Protein Engineering and Molecular Modeling

(Associate) Scientist Protein Engineering and Molecular Modeling

dsm-firmenich

Delft, Netherlands

We are seeking a skilled data scientist specializing in protein engineering and molecular modeling to join dsm-firmenich’s Computational Biotechnology team. In this role, you will model and optimize enzymes to support the development of innovative, sustainable bioproduction processes and specialty enzymes. You will translate structure–function insights into practical protein engineering strategies, from biodiversity exploration to library design. Working in multidisciplinary teams, you will collaborate closely with experts to scale molecular insights into real-world applications. This role offers a hands-on opportunity to contribute to impactful biotechnology innovations.

Your key responsibilities 

• Shape projects in collaboration with business partners, translating objectives into clear and actionable experimental plans
• Model protein structures to uncover structure–function relationships and design targeted mutant or diversity libraries
• Analyze, interpret, and communicate results effectively to stakeholders through reports and presentations
• Develop and apply machine learning and protein AI models to predict and improve structure–function outcomes
• Contribute to best practices and shared computational tools within the global data science and life sciences community
• Collaborate with cross-functional teams globally while applying modern software and ML practices, including Python and coding tools, to drive project success

You bring

• A PhD (or equivalent) in Biochemistry, Biophysical Chemistry, Bioinformatics, or Computer Science, with a focus on protein engineering and in silico design
• 2–4 years of experience in protein engineering and molecular modeling, applying modern data-driven approaches in areas such as metabolic engineering, enzymes, or biocatalysis
• Strong ability to quickly understand diverse proteins and enzymes, leveraging literature and data sources to assess scientific and business relevance
• Proven experience with bioinformatics and protein modeling tools (e.g., Rosetta, Schrödinger, Yasara) and databases such as UniProt, PDB, KEGG, or BRENDA
• Proficiency in Python and modern computational practices, with experience in ML tools, code management, and working in Unix/Linux environments; exposure to advanced simulations or protein AI tools is a plus
• Excellent problem-solving, collaboration, and communication skills, with a demonstrated track record of innovation and impact