(Senior) Scientist AI/ML for Protein and Metabolic Engineering

(Senior) Scientist AI/ML for Protein and Metabolic Engineering

dsm-firmenich

Delft, Netherlands

We are looking for a highly skilled AI/ML-focused data scientist to join dsm-firmenich’s Computational Biotechnology team, driving next-generation innovations in protein and metabolic engineering. In this role, you will lead the development of advanced, data-driven workflows for enzyme design, pathway optimization, and strain engineering. You’ll collaborate across disciplines to translate complex biological challenges into scalable AI-powered solutions. As a senior contributor, you’ll shape best practices, mentor colleagues, and influence strategic technology decisions. This is a high-impact opportunity to advance sustainable biotechnology and real-world applications of AI-enabled engineering.

Your key responsibilities 

• Lead the application of AI and data science to accelerate high-impact protein and metabolic engineering across key business segments
• Develop and continuously improve advanced models for DNA, RNA, proteins, and metabolic pathways, integrating them into engineering workflows
• Translate complex modeling results into clear, actionable insights for teams, stakeholders, and customers
• Establish and promote best practices, standards, and scalable platforms within the global data and life sciences community
• Monitor emerging advances in computational biology and AI, driving adoption of innovative methods with strategic value
• Collaborate closely with cross-functional teams worldwide, applying modern ML and software engineering practices to deliver project success

You bring

• A PhD (or equivalent) in Biochemistry, Biophysical Chemistry, Bioinformatics, Computer Science, or Artificial Intelligence, with a focus on computational approaches to protein and strain engineering
• 3–7 years of academic or industry experience applying data- and knowledge-driven methods in protein and/or metabolic engineering
• Hands-on experience with foundation models in biology, including fine-tuning and applying sequence, structure-aware, generative, and pathway models to real-world challenges
• Strong expertise in deep learning, with practical experience in architectures such as transformers, GNNs, and/or diffusion models, ideally incorporating biological priors
• Experience working with HPC environments and large-scale AI/ML workflows, including distributed computing and GPU-accelerated model training and deployment
• Proficiency in Python and modern ML practices, combined with strong problem-solving, collaboration, and communication skills, and a track record of innovation and impact