Cpl in partnership with our client Pfizer Grange Castle are currently recruiting for a

Senior Scientist: Process Modelling and Interpretable Machine Learning

The Manufacturing Intelligence (MI) team within Pfizer’s Global Technology & Engineering (GT&E) is responsible for driving the development and implementation of advanced analytics including AI/ML, soft sensor, advanced process control, and process condition monitoring solutions in support of manufacturing and future capabilities in Pfizer Global Supply (PGS).

As a member of MI, this role will have the opportunity to develop and implement advanced analytics, real-time soft sensors, machine learning, advanced process control and IIoT solutions/capabilities in manufacturing settings to achieve actionable insights and enable continued improvement for pharmaceutical manufacturing and quality operations.

Responsibilities

Technical contribution to high-impact projects that require data analytics, advanced modeling, and optimization expertise.
Identify high value opportunities for applying Advanced Analytics, Advanced Process Control (APC), Artificial Intelligence (AI), Machine Learning (ML) and Industrial Internet of Things (IIoT), and develop and deploy innovative fit-for-purpose solutions in manufacturing environment
Drive development of mathematical and machine learning models and support GMP implementation of such analytics solutions
Apply engineering principles, modeling tools, and experimental skills using data-rich lab/pilot/manufacturing equipment to improve process understanding and facilitate real-time process monitoring and control
Collaborate with cross-functional teams and key stakeholders, effectively communicate progress to management, and drive project progress in a timely manner.

Basic Qualifications

A PhD degree in relevant engineering major, mathematics, or computer science is preferred.
Expert-level knowledge in Python is a must. Experience in any of the following languages is a plus: R, Matlab, JavaScript.
Ability to perform data engineering on real world big-data ranging from structured time-series datasets with thousands of features, to unstructured image, text, audio and video data.
Track record in applying data science and machine learning methodologies to real-world data to generate insight and support decision making.
Ability to work collaboratively in diverse cross-functional teams on innovative solutions and tools with an open attitude towards fast learning
Knowledge of upstream and downstream Biopharmaceutical Manufacturing
Experience deploying Interpretable Machine Learning or Explainable AI and knowledge of Shapley values and plots
Demonstrated experience of story-telling with interpretability tools usable by technical experts and non-technical stakeholders
Use of exploratory analysis tools for abstractions such as feature visualization and attribution that aid scientists in interpreting and explaining machine learning model results
Independent, self-motivated personality with excellent oral and written communication skills

Preferred Qualifications

Expertise in first principles (thermodynamics, reaction modelling, heat transfer, mass transfer principles), hybrid modelling. Ability to develop practical process models for real-time applications is a strong plus.
Experience in cloud-based code development and deployment environments such as AWS SageMaker or Tibco.
Familiarity with cloud computing based data-warehouses such as Snowflake or Redshift, and relational SQL databases.
Hands on experience in deep learning and LVM for real-time monitoring and anomaly detection of time-series data and automated root cause analysis.
Experience in data visualization and real-time GUIs using Streamlit, Plotly, Spotfire, etc.
Familiarity with feedback control algorithms, real-time communication protocols, industrial process historians, and industrial automation platforms such as DeltaV and ASPEN.
Knowledge of Cell Culture, Fermentation and Vaccines Conjugation
Work Location Assignment: Hybrid, Flexible -dealing with USA