Postdoctoral Fellow – Ai/ml Enabled Bioprocess Modeling and Control

Pfizer · Pharma · MA

Seeking a Postdoctoral Fellow to develop AI/ML enabled bioprocess models and control strategies for recombinant protein production. The role involves creating hybrid mechanistic-data driven models, integrating omics data, applying ML/DL for prediction, and exploring agentic AI for model orchestration and transfer learning. Responsibilities include designing experiments, implementing model predictive control, validating models, and communicating results.

What you'd actually do

  1. Develop hybrid mechanistic–data driven models for mammalian cell culture processes supporting recombinant protein production.
  2. Integrate transcriptomic and other omics data as structured inputs for clone specific performance and stability prediction.
  3. Apply machine learning and deep learning methods for phenotypic clustering, parameter estimation, and performance prediction.
  4. Extend existing mechanistic bioprocess models to include additional physiological functions (e.g., amino acid metabolism, regulatory feedback loops) using kinetic, genome scale, or data driven modeling approaches.
  5. Design and implement model predictive control (MPC) frameworks using mechanistic and hybrid models for real time control of critical process variables (e.g., feeding strategies, metabolite control).

Skills

Required

  • PhD in Chemical Engineering, Biochemical Engineering, Bioengineering, Systems Biology, Computational Biology, or related field
  • 0-2 years postdoctoral experience
  • Scientific publications/presentations with at least one first-author publication
  • Mathematical modeling
  • Chemical/biochemical reaction kinetics
  • Mammalian cell culture processes
  • Scientific computing (Python, Julia, MATLAB)
  • Machine learning
  • Data-driven modeling
  • Model validation
  • Omics data integration (transcriptomics)

Nice to have

  • Control toolboxes
  • Optimization solvers
  • ML libraries
  • Process systems engineering
  • Model predictive control
  • Optimal control
  • Dynamic optimization
  • Modular, reusable AI/ML workflows
  • Transfer learning
  • Multi-task learning
  • Adaptive decision-making
  • Human-in-the-loop modeling
  • CHO cell physiology
  • Central carbon and amino acid metabolism
  • Regulatory mechanisms in bioprocessing
  • Experimental design and execution of cell culture experiments

What the JD emphasized

  • PhD in Chemical Engineering, Biochemical Engineering, Bioengineering, Systems Biology, Computational Biology, or a closely related field (0–2 years postdoctoral experience)
  • Successful record of scientific accomplishments evidenced by scientific publications and/or presentations with at least one first-author publication in a peer-reviewed journal
  • Strong foundation in mathematical modeling, chemical/biochemical reaction kinetics, and mammalian cell culture processes.
  • Proficiency in scientific computing using Python, Julia and/or MATLAB
  • Demonstrated expertise in machine learning and data-driven modeling, including regression, classification, clustering, and model validation.
  • Experience integrating omics data (especially transcriptomics) with mechanistic or hybrid models.

Other signals

  • Develop hybrid mechanistic–data driven models for mammalian cell culture processes
  • Integrate transcriptomic and other omics data
  • Apply machine learning and deep learning methods
  • Explore agentic AI frameworks to orchestrate model fitting, validation, and transfer learning