Associate Scientist, Post Doc Fellow, AI/ML & Computational Biology for Antigen Design

What you'll do

• Develop and deploy AI/ML architectures including protein language models, folding models, and geometric deep learning models.
• Design and optimize conformationally constrained viral antigens using predictive machine learning workflows.
• Integrate molecular dynamics simulations and energetic modeling with deep learning to capture dynamic conformational transitions.
• Use high-throughput experimental data from biophysical characterization platforms to iteratively retrain and refine candidate models.
• Translate computational breakthroughs into translatable vaccine designs by collaborating with structural biology and immunology experts.
• Author high-impact manuscripts and present research findings at major international conferences in the field of computational biology.

What we're looking for

• Must hold a PhD or be on track to receive one by spring 2027 in a related quantitative field.
• Demonstrated experience applying machine learning models to biomolecular data, including protein language models, folding models, or structural inverse-folding.
• Proficiency in Python and modern ML frameworks like PyTorch or JAX is required.
• Experience with high-performance computing (HPC), GPU workflows, version control, and reproducible software development is required.
• Proven record of independent research through first-author peer-reviewed publications, preprints, or presentations at major conferences.
• Experience with structural modeling suites and molecular dynamics tools (preferred).
• Working knowledge of biophysical and biochemical characterization methods and how experimental data informs model training (preferred).
• Experience with dynamic or oligomeric protein complexes that undergo conformational rearrangements (preferred).