AVP - Design Validation & Learning, Biotherapeutics

Lilly • San Diego, CA

1d • $267,000 - $391,600 • Onsite

About The Position

The AVP of Design Validation & Learning will define and execute the scientific strategy for evaluating, validating, and continuously improving Lilly’s de novo biologics design capabilities. The role establishes experimental learning systems, validation standards, benchmarking frameworks, and data-generation strategies that turn computational predictions into actionable scientific insights and strengthen future design capabilities.

This founding leadership position will build and lead a multidisciplinary team spanning model evaluation, active learning, computational biology, statistical methodology, physics-based modeling, and experimental learning. The AVP will ensure that experimental outcomes improve the platform’s ability to design therapeutic molecules. The role is based at Lilly’s Biotechnology Center in San Diego and supports an integrated generative design platform combining AI/ML, protein engineering, automation, structural biology, and high-throughput experimentation.

Requirements

• Ph.D. in computational biology, biophysics, computational chemistry, bioengineering, chemical engineering, physics, statistics, or a related STEM field, with at least 5 years of post-Ph.D. research experience; alternatively, an M.S. with at least 10 years of experience.
• At least 3 years of experience leading scientists or engineers as a formal people manager, including building or scaling a team.
• Demonstrated experience leading validation of machine-learning or physics-based predictions against experimental measurements in drug discovery, molecular design, or a related scientific setting.
• Proficiency in Python and applied statistics, including calibration, uncertainty quantification, experimental design, and quantitative evaluation methodologies.

Nice To Haves

• Experience partnering with experimental teams on assay or campaign design.
• Experience building benchmarking frameworks, validation suites, or evaluation systems adopted across multiple teams, research organizations, or discovery programs.
• Experience applying molecular dynamics, free-energy methods, enhanced sampling, or related simulation approaches to protein design, evaluation, or molecular understanding.
• Expertise in protein stability, aggregation, viscosity, expression, manufacturability, or developability prediction.
• Experience designing large-scale experimental datasets for model training, validation, or active learning.
• Experience with active learning, Bayesian experimental design, or sequential experimentation under constrained experimental budgets.
• Working knowledge of binding and biophysical measurements, including SPR, BLI, thermostability, expression, and related assay technologies.
• Proven ability to build cross-functional partnerships across computational, experimental, automation, and therapeutic discovery organizations to deliver shared scientific goals.
• Strong written and verbal communication skills, including translating complex computational, statistical, and experimental concepts for scientific leaders, experimental researchers, and executive stakeholders.

Responsibilities

• Define scientific strategy for evaluation, validation, and learning, including measures of model performance, design quality, and therapeutic impact.
• Establish rigorous benchmarks and validation standards that assess generalization, prospective design performance, biological relevance, experimental success, and failure modes.
• Create a closed computational-experimental learning system with experimental scientists, using predefined metrics to evaluate models, identify failure modes, and improve subsequent models and molecular designs.
• Determine where simulation, molecular modeling, and energy-based calculations add value and how physics-based approaches should be integrated with machine-learning approaches.
• Define which experiments should be performed next and partner with DMTA, automation, protein engineering, and discovery leaders to build proprietary data assets for model training, evaluation, and future design cycles.
• Embed AI capabilities in active discovery programs, identify opportunities for computational design to change program outcomes, and measure impact through novel molecular solutions, hit rates, design precision, experimental efficiency, and advancement of differentiated candidates.
• Establish platform-wide success metrics for model performance, design quality, experimental efficiency, and therapeutic outcomes, and ensure they are tracked and communicated.
• Build, recruit, develop, and lead an interdisciplinary organization; establish its culture, scientific standards, and talent strategy.
• Partner with data engineering, MLOps, computational infrastructure, and enterprise technology organizations to provide scalable data, training, inference, experimentation, and deployment capabilities.
• Represent the organization as an internal and external scientific leader through communication with senior leadership, publications, conferences, collaborations, and engagement with the scientific community.

Benefits

• Company bonus, depending in part on company and individual performance.
• Company-sponsored 401(k) eligibility.
• Pension.
• Vacation benefits.
• Medical, dental, vision, and prescription drug benefits eligibility.
• Flexible benefits, such as healthcare and dependent day care flexible spending accounts.
• Life insurance and death benefits.
• Certain time-off and leave-of-absence benefits.
• Well-being benefits, including an employee assistance program, fitness benefits, and employee clubs and activities.

What This Job Offers

• Job Type: Full-time
• Career Level: Executive
• Education Level: Ph.D. or professional degree