The Chan Zuckerberg Biohub Chicago is seeking to advance biological research and discovery by leveraging machine learning, statistics, and AI to develop new technologies and computational methodologies.
Requirements
- Demonstrated experience applying machine learning to biological problems, particularly involving proteins or immune recognition.
- Proficiency with protein language models (e.g., ESM2, EVO), structure prediction tools (e.g., AlphaFold2), and model interpretation techniques.
- Working knowledge of model development pipelines, including feature selection, regularization, and introspection.
- Familiarity with protein–protein interaction networks and the biophysical principles of molecular recognition.
- Strong coding and data skills, with an emphasis on reproducibility, clarity, and documentation.
- Experience collaborating closely with experimentalists to validate computational predictions.
- Familiarity with structural biology databases (e.g., PDB, TCR3d) and immune-specific resources (e.g., IEDB, VDJdb).
Responsibilities
- Develop and benchmark predictive models of immune interactions using AI/ML, protein language models, and structure prediction tools.
- Validate, interpret, and stress-test model predictions using external datasets and expert biological intuition.
- Collaborate with lab scientists and computational researchers to ensure real-world relevance and robust model evaluation.
- Create intuitive visualizations and interfaces to interpret molecular interactions and support downstream experimentation.
- Contribute to impactful publications, open-source software, and potential translational applications through patents or partnerships.
Other
- PhD in Immunology, Structural Biology, Biochemistry, Computational Biology, or a related field.
- Excellent collaborative and communication skills, with experience in interdisciplinary teams.
- Prior work in immunoinformatics, AI-guided protein design, or immune repertoire analysis.
- History of impactful publications or open-source contributions in computational biology or AI/ML.
- Background in data curation and management for large-scale genomic datasets.
