Postdoctoral Scholar-Pharmaceutical Sciences

THIS IS A GRANT-FUNDED POSITION OFFERED AS A ONE-YEAR CONTRACT, RENEWABLE ANNUALLY BASED ON PERFORMANCE AND THE AVAILABILITY OF FUNDING

JOB SUMMARY/ESSENTIAL JOB FUNCTIONS: The Roy Laboratory has an immediate opening in Artificial Intelligence (AI) in small molecules drug discovery for a talented and motivated Postdoctoral Scholar to join our interdisciplinary team focused on accelerating small molecule drug discovery. The ideal candidate will have a strong background in artificial intelligence, machine learning, and computational chemistry, with a deep understanding of molecular modeling, cheminformatics, and drug discovery pipelines. You will contribute to the development and application of AI-driven models to identify and optimize novel therapeutic compounds.

1. Develops and applies AI approaches for small molecule virtual screening, de novo molecule generation, lead optimization, and property prediction.
2. Integrates and analyzes multi-modal datasets, including chemical structures, bioactivity data, omics profiles, and structural biology information, to create predictive and generative models for small molecule development.
3. Collaborates closely with medicinal chemists, structural biologists, and pharmacologists to interpret model outputs and guide experimental design.
4. Designs, implements, and evaluates novel AI/ML algorithms tailored to chemical space exploration and drug discovery.
5. Evaluates and benchmarks model performance using rigorous statistical and domain-relevant criteria.
6. Contributes to the development of computational platforms and pipelines for end-to-end drug discovery tasks.
7. Publishes research findings in top-tier journals and present at scientific conferences.
8. Stay abreast of the latest developments in AI and computational drug discovery and recommend innovative tools and techniques.

• PhD in Computer Science, Computational Chemistry, Bioinformatics, or related field.
• Proficiency in Python and scientific computing tools (NumPy, Pandas, Jupyter).
• Strong experience with AI/ML frameworks: PyTorch, TensorFlow, scikit-learn, XGBoost.
• Familiarity with graph neural networks (e.g., DGL, PyTorch Geometric) and/or generative models (e.g., VAEs, GANs, diffusion models).
• Proven experience in cheminformatics: RDKit, DeepChem, Open Babel.
• Strong understanding and experience of model evaluation techniques (e.g., cross-validation, ROC-AUC, precision-recall) and bias mitigation in imbalanced or noisy datasets.
• Experience with molecular representations (e.g., SMILES, SELFIES, molecular graphs) and datasets (e.g., ChEMBL, PubChem, ZINC, BindingDB).
• Hands-on experience with AI tools/platforms such as REINVENT, MolBERT, Chemprop, DeepDock, DiffDock, or MoleculeNet.
• Familiar with drug discovery concepts, including QSAR modeling, molecular docking, and lead optimization.

PREFERRED:

• Knowledge of protein–ligand interaction modeling, including experience with docking software (e.g., AutoDock Vina, GOLD, GNINA) and MD simulation packages (e.g., AMBER, NAMD, Desmond).
• Familiarity with protein structure prediction tools, especially AlphaFold, and integration of predicted structures into modeling workflows.
• Hands-on experience with AI-driven molecular design platforms, such as REINVENT, MolBERT, Chemprop, DeepDock, DiffDock, or benchmark datasets like MoleculeNet.
• Understanding of synthetic accessibility and feasibility, including cheminformatics-based estimations.
• Exposure to retrosynthesis planning tools, such as ASKCOS, AiZynthFinder, IBM RXN, and related automated synthesis platforms.
• Experience with high-performance computing (HPC) clusters and/or cloud-based AI/ML environments (AWS, GCP, Azure), including resource management, job scheduling, or distributed training.