Senior Scientist - Process Modelling

Sanofi•Framingham, MA

4d•$100,500 - $145,167•Onsite

About The Position

The global CMC (Chemistry Manufacturing and Control) function is responsible for process development activities in R&D, designing appropriate control strategy to deliver processes of optimum product quality, supplying material for clinical trials and ensuring robust transfer of the process to our commercial organization. The CMC organization is undergoing a substantial digital transformation that is transforming our experimental workflows. The digitalization of the lab activities provides automated access to experimental data, contextualization and centralization of the data accessible to scientists across all CMC sites and functions. As experimental data becomes readily available, the data consumption strategy is taking a central role in the department, with a strong focus on data preparation, data flow and data consumption, feeding applications developed in-house and commercial software used across CMC for data visualization, data modeling and advanced data analytics. In this role, you will be based in the process modelling team within the CMC Data Science group. Our team provides process modeling and data analytics support for cell line selection, cell culture process development, process scale-up and technology transfer across microbial hosts, mammalian hosts, and gene therapies. Join the engine of Sanofi’s mission — where deep immunoscience meets bold, AI-powered research. In R&D, you’ll drive breakthroughs that could turn the impossible into possible for millions.

Requirements

PhD in Chemical Engineering, Biochemical Engineering, Process Systems Engineering, Bioengineering, Biomedical Engineering, or related engineering or scientific discipline OR Master's degree in any of the above fields
PhD holders: Minimum 1 year of relevant experience (academic, research assistantship, or industry experience will be considered)
Master's holders: Minimum 4 years of relevant industry or research experience
Demonstrated experience developing dynamic models of bioreactor or cell culture processes
Proficiency in at least one scientific computing language: Python, MATLAB, Julia, or R

Nice To Haves

Experience developing dynamic mechanistic models using ordinary differential equations (ODEs), kinetic rate laws, mass balances, parameter estimation, and model validation
Strong understanding of mammalian cell culture process development, including fed-batch and/or perfusion bioreactor operation
Proven track record of developing and deploying bioreactor digital twins, process models, or advanced monitoring tools in an industrial biopharmaceutical environment
Understanding of bioreactor engineering principles: oxygen transfer, mixing, mass transfer, CO₂ stripping, kLa, shear, scale-up and scale-down models
Experience with perfusion bioreactor modeling: cell retention, bleed strategies, media exchange, residence time, productivity, and steady-state operation
Experience with multivariate statistical process monitoring techniques such as PCA or PLS for early fault detection
Familiarity with soft sensors, state estimation, Kalman filtering, moving-horizon estimation, or real-time process monitoring and model predictive control
Track record of peer-reviewed publications in process modeling/simulation for upstream biopharmaceutical processes
Prior experience working with international/global teams across multiple time zones and locations

Responsibilities

Develop, calibrate, and validate bioreactor dynamic models to simulate, optimize, and control recombinant protein production and product quality attributes.
Transfer and deploy bioreactor models in a commercial manufacturing environment to support process monitoring and forecasting (digital shadows) and/or real-time bioreactor optimization and control (digital twins).
Work as part of matrix project teams with cell-culture development, process development, analytical, automation, and data science teams across R&D and manufacturing.
Communicate model assumptions, uncertainty, limitations, and process interpretation to technical and non-technical stakeholders
Maintain reproducible computational workflows using appropriate coding, documentation, version control, and data-management practices.
Act as a change agent to support the implementation of process modeling in established cell culture process development workflows.
Document progress against deliverables with rigorous scientific communication via technical presentations, reports and, when appropriate, scientific publications.