Associate Principal Scientist, Deep Learning Engineer within Data-Rich Experimentation (DRE) Full-time

Associate Principal Scientist, Deep Learning Engineer Within Data-Rich Experimentation (Dre)

In this role, the chosen candidate will work with a team of scientists tasked with identifying, developing, and deploying data-rich technologies aimed at improving the manner in which process understanding is gathered. The tools that we develop are as diverse as the team developing them, and in this Associate Principal Scientist role, the chosen candidate will leverage fundamental process modeling, machine learning, and other innovative data science approaches to enable our process research and development efforts across our company's biologics and vaccines portfolio.

Our DRE organization is responsible for the invention and application of new data-rich tools to support the scientists across process research and development at our company. We aspire to embed data-intense technologies into the fabric of our company's process development culture. This Associate Principal Scientist role is a scientific position tasked with solving complex process research and development challenges in an interdisciplinary, collaborative environment via invention, development, and application of cutting-edge process modeling including novel deep neural network architectures and especially their combination with physics and theory through hybrid methods. Ultimately, through the development, application, and deployment of these capabilities across our multi-modality pipeline, we aim to elucidate a deeper understanding and optimization of our processes and drive enhanced decision making for improving the speed and quality of development for diverse medicines and vaccines.

In this Associate Principal Scientist role, the chosen candidate will combine process modeling and deep learning techniques to help advance process-focused scientific research. This includes, but is not limited to, developing mechanistic, hybrid, or data-driven models for chemical synthesis and isolation, cell culture, fermentation, biomolecule separations; working closely alongside pipeline project teams to extract impactful insights from experimental data for manufacturing process design; employing process models to accelerate and enhance laboratory development through ML-assisted optimal experiment design; applying physics-based and hybrid models to guide and de-risk scale-up/scale-down during technology transfer and commercialization; developing new hybrid machine learning frameworks based on customized deep learning architectures and their integration with physics-based models or structures; and collaborating with enterprise IT colleagues for the automated scaling, training, and serving of such models to an extensive process development organization. As such, the chosen candidate should have a robust background in machine learning with an emphasis on the intersection of modeling and manufacturing process development.

In addition to a passion for computational process modeling and machine learning, the chosen candidate should have excellent interpersonal, communication, and collaboration skills. The chosen candidate should embrace and model our core values of diversity and inclusion, including fostering a supportive culture where all can thrive. The chosen candidate should be able to effectively collaborate in a dynamic, integrated, and multidisciplinary team environment. The chosen candidate should demonstrate a clear ability to perform impactful scientific innovation in a team-oriented manner that builds trusted partnerships across vast stakeholder networks. The chosen candidate should have a demonstrated ability to publish and present research, including an established track record of interaction with the broader academic community. The chosen candidate will join a diverse group of scientific problem solvers who are dedicated to creating the life-changing medicines and vaccines of tomorrow.

Education minimum requirement:

• A Ph.D. in engineering, biology, chemistry or a closely-related field with at least 3 years of industrial/pharmaceutical experience
• A M.S. in engineering, biology, chemistry or a closely-related field with at least 5 years of industrial/pharmaceutical experience
• A B.S. in engineering, biology, chemistry or a closely-related field with at least 7 years of industrial/pharmaceutical experience

Required experience and skills:

• Background and experience in process modeling, scientific machine learning, deep learning, and technology deployment.
• Expertise in python with hands-on experience in deep learning frameworks and libraries (pytorch, jax, tensorflow, or similar).
• High motivation and enthusiasm for novel technology development; passion for modernizing chemical and bioprocess development practices.
• Excellent communication skills, demonstrated creativity, adaptive problem-solving, and effective interpersonal skills for delivering complex technical solutions in a dynamic cross-functional environment
• Demonstrated scientific expertise evidenced through impactful journal publications and/or conference presentations.

Preferred experience and skills:

• Experience in developing novel process models for dynamical systems, process control, or digital twins for chemical or biological systems through physics-based, mechanistic, or hybrid model frameworks.
• Background in laboratory chemical or biochemical research, cell culture, or fermentation process design, development, or optimization and experience applying or developing new digital or data-rich technologies to extract insights from complex laboratory data
• Familiarity with MLOps practices and workflows (automated training, documentation and monitoring, deployment and integration) and ability to collaborate with IT stakeholders for technology deployment at scale.
• Experience in the new technology development and deployment with an understanding of technology adoption frameworks, including a successful track record of technology change management.