Director, Design Validation & Learning, Biotherapeutics

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. At Lilly, we unite caring with discovery to make life better for people around the world. For more than 25 years, Lilly's Biotechnology Discovery Research (BioTDR) organization has advanced novel antibody and peptide therapeutics from concept through clinical development to market in areas of high unmet medical need. This role is based at the Lilly Biotechnology Center in San Diego, where we are expanding our computational capabilities to build a generative design platform. By bringing together AI/ML, protein engineering, automation, structural biology, and high-throughput experimentation, BioTDR is creating an integrated de novo design platform capable of generating, ranking, and optimizing novel therapeutic antibodies and other biotherapeutics with improved activity, safety, manufacturability, and target coverage. Designs are rapidly evaluated through experimental validation, creating a continuous learning cycle that strengthens both models and discovery outcomes. The program is supported by dedicated capacity on LillyPod, our wholly owned 1,016-GPU NVIDIA Blackwell Ultra SuperPOD. Help us push the de novo protein design frontier beyond binders to molecules that can become medicines, faster. Ready to make an impact? Join us. Primary Responsibilities Our Generative Design platform has three pillars: Generative Foundation Models, Generative Protein Design & Optimization, and Active Learning & Design Validation. The Director of Design Validation & Learning will lead the scientific execution of validation and continuous learning for Lilly's de novo biologics design capabilities. Working at the intersection of model development, generative design, and experimental science, you will connect computational predictions with experimental measurements and translate those learnings into improvements in models and molecular design. You will lead a validation and learning workstream, establishing rigorous benchmarks, designing prospective validation studies, and identifying what experimental evidence tells us about model strengths, limitations, and failure modes. You will also advance physics-based computational approaches where they can strengthen design capability on challenging problems. This is an opportunity for a scientific leader who wants to ensure that every design cycle generates actionable learning that improves the next. Responsibilities Model evaluation and benchmarking. Develop rigorous benchmarks for accuracy, generalization, designability, novelty, and prospective success. Evaluate models and design approaches against experimental outcomes and challenging out-of-distribution problems. Prospective validation and closed-loop learning. Design informative validation studies with experimental scientists, prioritize molecules for testing, interpret experimental results, identify model and design failure modes, and translate findings into actionable improvements for subsequent design cycles. Model calibration against experimental data. Establish ground-truth-driven calibration measures for structure confidence, binding and affinity prediction, developability prediction, and probability of therapeutic success. Physics-based computation. Build and validate molecular dynamics, energy-based, and structure-based methods within the design pipeline. Establish evidence for where these approaches improve model or design capability and integrate them with ML-based methods where appropriate. Purposeful data generation and active learning. Partner with DMTA, automation, protein engineering, and computational teams to identify informative experiments and generate data that supports model refinement, evaluation, active learning, and successive design rounds. Partner with therapeutic discovery teams. Identify biological problems where AI-enabled design can meaningfully affect program outcomes and translate computational predictions and experimental learnings into actionable experiments and therapeutic candidates. Lead a high-performing team and provide technical leadership. Lead the validation and learning workstream, develop scientists on the team, provide sustained technical mentorship, establish rigorous scientific standards, and guide technical priorities and execution. Drive cross-functional learning. Partner closely with Generative Foundation Models and Generative Protein Design & Optimization teams to ensure experimental findings, model limitations, and validation results inform subsequent model and design iterations. Scientific influence. Communicate validation results, including negative and ambiguous findings, clearly and objectively. Publish and present scientific work, benchmark against external alternatives using the program's standard evaluations, and influence technical direction across teams. Basic Requirements Ph.D. in computational biology, biophysics, computational chemistry, bioengineering, chemical engineering, physics, statistics, or a related STEM discipline with 3&#43; years of relevant experience; or an M.S. with 6&#43; years; or a B.S. with 8&#43; years of relevant experience. Track record of leading efforts that compare computational predictions with experimental measurements and translating the findings into scientific or technical decisions. Strong Python and applied statistical skills, including calibration, uncertainty analysis, and quantitative evaluation. Additional Preferences Track record in benchmarking or evaluation-suite development. Hands-on experience with molecular simulation, energy-based, or structure-based modeling at scale.</spa