Process Development Engineer III, Data Science

Machine Learning Engineer

Regeneron's Data Enablement and Analytics (DEA) team within Preclinical Manufacturing and Process Development (PMPD) is seeking a Machine Learning Engineer to develop, build and deploy analyses and machine learning models that support bioprocess development. This role is ideal for a data scientist with a strong foundation in chemical or biomedical engineering and a passion for building impactful solutions in close collaboration with scientists and process engineers.

You will work at the intersection of software engineering, data science, and bioprocess domain expertise—developing models that will be put into action within PMPD's laboratory and manufacturing operations. You will mentor and coordinate citizen data scientists. Your work will streamline workflows, enable automation, and accelerate decision-making across PMPD.

• Partner closely with scientists, engineers, and analysts to understand bioprocess workflows and identify high‑impact data science opportunities.
• Acquire, clean, and structure complex datasets to enable scalable, repeatable analyses.
• Design, develop, and apply advanced analytics and machine learning models to drive data‑informed decision‑making.
• Deploy models into production environments, enabling automated and autonomous operations where appropriate.
• Lead, mentor, and coordinate citizen data scientists on critical initiatives across PMPD
• Enhance, maintain, and extend existing analytics tools and platforms to support new use cases and evolving business needs.
• Contribute as an active member of Agile teams within a Scaled Agile Framework, supporting planning, delivery, and continuous improvement.
• Continuously evaluate emerging technologies and methodologies to strengthen data science capabilities within the organization

• Bachelor's or Master's degree in Chemical Engineering, Biomedical Engineering, or a related discipline. 5-7 years of experience in bioprocess development, pharmaceutical manufacturing, or a closely related domain.
• Demonstrated ability to apply machine learning and predictive analytics to complex, real‑world problems.
• Strong programming skills in Python and SQL, with a solid understanding of data modeling and database design.
• Experience working in Linux/Unix environments and using Git for version control and collaboration.
• Excellent communication skills and a collaborative mindset, with the ability to partner effectively with scientists, engineers and analysts, while mentoring citizen data scientists.
• Familiarity with Dev Ops and deployment technologies such as Kubernetes, NixOS, and Jenkins.
• Experience with Operational Technology and analytics platforms (e.g., PI Historian, OPC, MQTT, Dataiku, Seeq) is a plus.