Senior Scientist, Ai‑enabled Structural Biology

Pfizer Pfizer · Pharma · CT

Senior Scientist role at Pfizer focused on integrating AI/ML with structural biology for drug discovery. The role involves applying generative AI and computational protein design (like AlphaFold, RFdiffusion) to create custom structural tools, processing cryo-EM data with AI/ML, and leading design-test-learn workflows. It requires expertise in structural biology techniques and computational methods, with a focus on accelerating drug design through AI-enabled capabilities.

What you'd actually do

  1. Apply and adapt generative AI and computational protein design methodologies (e.g., AlphaFold, RoseTTAFold, RFdiffusion, ProteinMPNN) to design, optimize, and engineer custom structural tools – including de novo binders, fusion proteins, and fiducials – to enable structurally challenging cryo-EM targets.
  2. Execute and adapt computational protein design workflows in HPC environments, including data preparation, job execution, and integration into iterative design–test–learn cycles, with an emphasis on scalable, high-throughput applications for large-scale screening and discovery.
  3. Own end-to-end structural biology strategies, including construct engineering, sample preparation, hands-on cryo-EM structure determination, and mechanistic interpretation of complex systems.
  4. Apply and adapt AI/ML-enabled approaches in cryo-EM data processing and model building workflows; develop or implement automated, scalable pipelines to support analysis of large and complex datasets.
  5. Establish integrated data and analysis workflows that connect computational design with experimental outcomes, leveraging high-quality datasets to inform, validate, and refine next-generation AI/ML models in collaboration with experimental and computational partners.

Skills

Required

  • Ph.D. in Structural Biology, Biochemistry, Biophysics, Computational Biology, or a closely related discipline
  • Innovation in protein design and engineering
  • Cryo-EM expertise
  • AI/ML-enabled approaches in cryo-EM data processing
  • Structure prediction software (e.g., AlphaFold, RoseTTAFold)
  • Generative models (e.g., protein language models, diffusion models like RFdiffusion)
  • HPC environments for computational workflows
  • Python scripting for automation
  • Experimental triage for challenging systems
  • Integration of structural and functional data
  • Cross-functional team collaboration
  • Scientific communication and reporting

Nice to have

  • Breadth of experience across multiple target classes (GPCRs, transporters, ion channels, etc.)
  • Familiarity with pharmacology, biochemistry, or biophysical assays
  • Developing scalable experimental strategies
  • Scientific leadership and mentoring

What the JD emphasized

  • proven track record of innovation in protein design and engineering
  • Hands-on expertise in cryo-EM
  • familiarity with AI/ML-enabled approaches
  • Proficiency with current structure prediction and protein design software
  • familiarity with state-of-the-art generative models
  • Experience working with HPC environments
  • using scripting (e.g., Python) to automate and operationalize these workflows for high-throughput, large-scale screening
  • Strong experience in experimental triage for challenging or conformationally heterogeneous systems
  • demonstrated ability to integrate structural and functional data
  • Proven ability to work effectively in cross‑functional, multidisciplinary teams
  • track record of presenting complex scientific findings to diverse audiences and contributing to scientific reports and publications

Other signals

  • AI-guided protein design
  • AI/ML-enabled data analysis
  • generative AI and computational protein design methodologies
  • AI/ML-enabled approaches in cryo-EM data processing