Director, Molecular AI & Federated Learning

At Lilly, the work is demanding because patients are waiting. We unite caring with discovery to help make life better for people around the world, knowing that every decision, every detail, and every day matters. Headquartered in Indianapolis, Indiana, our over 50,000 employees around the globe take on complex challenges to discover and deliver life-changing medicines, strengthen how health is understood and managed, and support the communities we serve.

This is hard, urgent, selfless work—but it’s work worth doing. If you’re driven by purpose and ready to bring your best to work that truly matters for patients, we invite you to join us.

Lilly Catalyze
360 is a comprehensive approach to enabling the early-stage biotech ecosystem by democratizing access to infrastructure, expertise, and resources. Through its interconnected pillars—Lilly Ventures, Lilly Gateway Labs, Lilly ExploR&D, and Lilly Tune Lab—Catalyze
360 strategically removes barriers that traditionally block bold science from becoming life-changing medicines, providing biotechs with flexible combinations of capital, physical lab space, R&D capabilities, AI/ML tools, and decades of enterprise learning.

The Director, Molecular AI & Federated Learning is a senior technical leadership role within the Tune Lab platform, setting the technical vision that unites privacy-preserving federated learning with generative small-molecule design. This position pairs deep expertise in medicinal chemistry, ADMET prediction, and molecular optimization with advanced capabilities in federated foundation models and multi-task learning, and is responsible for the predictive and generative models that accelerate small-molecule lead optimization and candidate selection across the Tune Lab federated network.

As a technical director, the role leads through vision, methodological rigor, and mentorship—guiding scientists and shaping research strategy across internal teams and external biotech partners—rather than through formal people management.

• Technical Vision & Research Strategy:
  Set the technical direction for federated learning and molecular AI across Tune Lab—defining a research agenda that unifies privacy-preserving foundation models, multi-task learning, and generative small-molecule design, and aligning it with platform and portfolio priorities.
• Technical Leadership & Mentorship:
  Serve as a principal technical authority and mentor for data scientists and engineers—guiding experimental design, reviewing methods and code, and raising the scientific bar across the team, while influencing technical decisions across disciplines internally and with external partners.
• Federated Foundation Models:
  Architect novel deep learning architectures (e.g., Transformer and graph neural network–based) for large-scale federated pre-training on unlabeled or partially labeled data distributed across multiple partner sources.
• Semi-Supervised & Self-Supervised Learning:
  Advance state-of-the-art semi-supervised and self-supervised methods (e.g., contrastive learning, masked auto-encoding) tailored to the constraints of federated learning, such as communication bottlenecks and data heterogeneity.
• Federated Optimization & Aggregation:
  Develop robust, communication-efficient aggregation strategies (e.g., Fed Avg, Fed Prox, SCAFFOLD) that remain stable for large, complex models and handle non-IID data across clients.
• Scalability, Simulation & Performance:
  Profile and optimize the computational performance—memory, latency, and communication cost—of federated training and inference for scale, and build high-fidelity simulation environments to test, debug, and benchmark federated strategies before real-world deployment.
• Federated Multi-Task Learning:
  Architect multi-task learning models that leverage shared representations across related endpoints to improve predictive performance and data efficiency in a federated ecosystem, where each client may hold data for only a subset of tasks.
• Data & Task Heterogeneity:
  Design algorithms that address extreme task and feature heterogeneity across clients—personalized models, meta-learning, and…