Director, Molecular AI & Federated Learning

Role: Senior technical leader in Lilly TuneLab's molecular AI and federated learning platform, focused on drug discovery innovation. Responsibilities: define research strategy and vision for privacy-preserving federated models, lead development of deep learning architectures (Transformers, GNNs) for molecular design, and guide multi-task, semi-supervised, and generative modeling efforts to optimize small-molecule lead candidates. Mentor scientists and influence cross-disciplinary research; ensure robust, scalable federated algorithms across heterogeneous data sources and enhance molecule property prediction, ADMET profiling, and scaffold hopping using advanced AI techniques. Qualifications: PhD in Computer Science, Chemistry, or related field; 5+ years post-PhD experience applying machine learning to drug discovery, with a preference for 8+ years. Skills: deep expertise in federated learning, molecular modeling, cheminformatics (RDKit, DeepChem), GNNs, and ML frameworks (PyTorch); strong understanding of medicinal chemistry, ADMET, synthesis feasibility, and PK/PD principles. High-Value: focus on in silico drug discovery, federated multi-task learning, generative chemistry, and AI-driven optimization within biotech collaborations. Stakeholder interaction includes internal research teams and external biotech partners. Location: Indianapolis, San Francisco, or Boston with up to 10% travel.