Director, Design Validation & Learning, Biotherapeutics

Lilly•San Diego, CA
•$193,500 - $338,800•Onsite

About The Position

The Director of Design Validation & Learning will lead the scientific execution of validation and continuous learning for Lilly's de novo biologics design capabilities at the Lilly Biotechnology Center in San Diego. Working across model development, generative design, and experimental science, the role connects computational predictions with experimental measurements and translates the resulting learnings into improvements in models and molecular design. The position leads a validation and learning workstream by establishing rigorous benchmarks, designing prospective validation studies, and determining what experimental evidence reveals about model strengths, limitations, and failure modes. It also advances physics-based computational approaches where they can strengthen design capabilities. The role works with experimental scientists and cross-functional teams to make each design cycle generate actionable learning that improves subsequent design cycles.

Requirements

  • Ph.D. in computational biology, biophysics, computational chemistry, bioengineering, chemical engineering, physics, statistics, or a related STEM discipline with 3+ years of relevant experience; or an M.S. with 6+ years; or a B.S. with 8+ years of relevant experience.
  • Track record of leading efforts that compare computational predictions with experimental measurements and translate findings into scientific or technical decisions.
  • Strong Python and applied statistical skills, including calibration, uncertainty analysis, and quantitative evaluation.

Nice To Haves

  • Track record in benchmarking or evaluation-suite development.
  • Hands-on experience with molecular simulation, energy-based, or structure-based modeling at scale.
  • Experience collaborating with experimental teams on assay or campaign design.
  • Expertise in antibody or VHH developability prediction.
  • Proficiency in experimental design, active learning, or sequential experimentation under constrained experimental capacity.
  • Experience with SPR, BLI, thermostability, expression, or related assay data.
  • Experience using automated or high-throughput laboratories as a structured data source for model evaluation or learning.
  • Experience leading a project team, mentoring scientists, or serving as technical lead of a cross-functional effort.
  • Strong written and verbal communication skills with computational and experimental scientists, including clear reporting of negative results, ambiguous findings, model limitations, and experimental evidence.

Responsibilities

  • 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.
  • Design informative prospective validation studies with experimental scientists, prioritize molecules for testing, interpret experimental results, identify model and design failure modes, and translate findings into improvements for subsequent design cycles.
  • Establish ground-truth-driven calibration measures for structure confidence, binding and affinity prediction, developability prediction, and probability of therapeutic success.
  • 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.
  • Partner with DMTA, automation, protein engineering, and computational teams to identify informative experiments and generate data for model refinement, evaluation, active learning, and successive design rounds.
  • Partner with therapeutic discovery teams to identify biological problems where AI-enabled design can affect program outcomes and translate computational predictions and experimental learnings into actionable experiments and therapeutic candidates.
  • Lead the validation and learning workstream, develop scientists, provide technical mentorship, establish rigorous scientific standards, and guide technical priorities and execution.
  • Partner with Generative Foundation Models and Generative Protein Design & Optimization teams so experimental findings, model limitations, and validation results inform subsequent model and design iterations.
  • Communicate validation results, including negative and ambiguous findings, clearly and objectively; publish and present scientific work, benchmark against external alternatives using program-standard evaluations, and influence technical direction across teams.

Benefits

  • Company bonus, depending in part on company and individual performance.
  • Eligibility to participate in a company-sponsored 401(k).
  • Pension.
  • Vacation benefits.
  • Eligibility for medical, dental, vision, and prescription drug benefits.
  • Flexible benefits, including healthcare and/or 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.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service