Protein Data Scientist

at  International Flavors Fragrances

Job Summary
The short version
Enzyme engineering is undergoing a paradigm shift thanks to lab automation and AI solutions. We are early adopters and are already reaping benefits of our investments. Now we are ready for the next step and are overhauling our workflows to streamline them for an end-to-end data-driven and highly automated ML based design process. We are looking for a Protein Data Scientist to accelerate our efforts and we hope it’s you!
Who we are
IFF’s Health & Biosciences division is a global leader in biotechnology. The IFF laboratories in Leiden have a long and dynamic history that goes back to the beginnings of modern biotechnology, to become the world market leader in sustainable bio-solutions. The R&D team in Leiden houses 35 creative, multi-disciplinary scientists from 13 different nationalities.
Our R&D team develops microbial cell factories and engineers enzymes for applications in the areas of food & beverages, home & personal care, animal nutrition and health, grain processing and more. We implement all steps in developing and engineering, from business idea and the use of generative AI to sample genetic diversity, to assay design, high-throughput screening, full-scale testing and manufacturing at our production plants.
The position
We are looking for an experienced engineer at the interfaces of biochemistry, machine learning and software development. As part of our team, you will identify the state-of-the-art in data-driven methods for library design, adjust them to our purposes and help implement them for direct use in business projects.
In our team, machine learning staff, molecular biologists, biochemists, and automation hardware engineers work side-by-side. Improvements are deployed with minimal delay, and you can expect to have large impact on the value of our products.
As Protein Engineering Data Scientist, you will help to define and benchmark ML-based design strategies that scales and seamlessly integrates with our high-throughput cloning and screening workflows. You have freedom to find preferred 3rd party technologies as well as deciding on the components and models that you prefer us to develop internally.
The Leiden R&D team is highly skilled and operates with a start-up mentality and a sharp focus on continuous improvement.

Responsibilities and Tasks

• Define and benchmark data-driven strategies for different use-cases of enzyme library design that scales to several engineering cycles per month.
• Implement a state-of-the-art, ML driven workflow that enables a high cadence and high-volume design-clone-screen cycle.
• Maintain the platform, monitor and benchmark performance, suggest and implement improvements.
• Identify and onboard 3rd party services and tools to offload responsibilities and let us focus on differentiating activities.
• Document, communicate and teach colleagues best-practices.

Qualifications

Required:

• A Bachelor’s, Master’s or PhD degree in a relevant technical field
• Expertise in statistical inference
• Comprehensive knowledge of machine learning - particularly generative natural (protein) language processing models
• Passion and documented experience with writing high-quality, structured and maintainable code (we mostly code in Python)
• Affinity for the life sciences, particularly biochemistry

It would be great if you:

• Have familiarity with MLops
• Like to write tests for your code
• Have experience with analyzing biochemical assays, control of noise, bias and design of experiments
• Have experience with applied enzyme engineering

We emphasize reaching goals through a collaborative effort. It is essential that you can use your good interpersonal and communication skills to achieve results together with others.
Fluency in spoken and written English is expected.

We offer

• The opportunity to grow professionally and to develop a long career in Biotech
• Position in a dynamic team of inspired, innovative and highly skilled scientists
• An energetic work environment created by inclusive and multicultural team
• Competitive salary and attractive compensation and benefits, such as:
• Individual Choice Budget of 8% of the annual base salary, employee choice to be paid in monthly instalments or to exchange for additional time off up to 15 extra days per year
• 25 vacation days and 3 bridge days, of which 2 of them are determined by the employer
• Annual Incentive Plan

We are a global leader in taste, scent, and nutrition, offering our customers a broader range of natural solutions and accelerating our growth strategy. At IFF, we believe that your uniqueness unleashes our potential. We value the diverse mosaic of the ethnicity, national origin, race, age, sex, or veteran status. We strive for an inclusive workplace that allows each of our colleagues to bring their authentic self to work regardless of their religion, gender identity & expression, sexual orientation, or disability.
Visit
IFF.com/careers/workplace-diversity-and-inclusion
to learn mor

• Define and benchmark data-driven strategies for different use-cases of enzyme library design that scales to several engineering cycles per month.
• Implement a state-of-the-art, ML driven workflow that enables a high cadence and high-volume design-clone-screen cycle.
• Maintain the platform, monitor and benchmark performance, suggest and implement improvements.
• Identify and onboard 3rd party services and tools to offload responsibilities and let us focus on differentiating activities.
• Document, communicate and teach colleagues best-practices