Director, AI/ML - Generative Foundation Models for Biotherapeutics

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

About The Position

Lilly’s Biotechnology Discovery Research organization is expanding its computational capabilities to build an integrated generative design platform for therapeutic antibodies and other biotherapeutics. The platform combines AI/ML, protein engineering, automation, structural biology, and high-throughput experimentation. Designs are experimentally evaluated in a continuous learning cycle to improve models and discovery outcomes. The program has dedicated capacity on LillyPod, a company-owned 1,016-GPU NVIDIA Blackwell Ultra SuperPOD. This role is based at the Lilly Biotechnology Center in San Diego. The Director of Generative Foundation Models will lead development of protein and antibody foundation models and validate their performance against experimental outcomes. The role is accountable for generative model families across architecture, training strategy, and validation, and will help define the program’s technical agenda with leadership. The Director will lead AI researchers and ML infrastructure engineers, provide direct technical guidance, and remain closely involved in the scientific and technical work.

Requirements

  • Ph.D. in computer science, mathematics, physics, computational biology, or a related quantitative field, with at least 3 years of relevant research experience after the Ph.D.; or an M.S. with at least 6 years of relevant experience.
  • Experience serving as technical lead of a multi-person modeling effort.
  • First-author or equivalently attributable contribution to a structure-based generative model.
  • Track record of carrying projects end to end.
  • Experience training deep learning models on multi-node infrastructure.
  • Strong Python and PyTorch skills.

Nice To Haves

  • Depth in equivariant architectures, diffusion or flow matching on structure, and graph transformers.
  • Experience with inverse folding, side-chain packing, all-atom generation, or conformational ensembles.
  • Work on uncertainty quantification or confidence prediction validated against experimental outcomes, not only held-out structures.
  • Contribution to a de novo binder or antibody design effort that reached experimentally validated designs.
  • Antibody or VHH experience.
  • Experience improving model efficiency by building smaller or faster models at equal accuracy.
  • Experience mentoring junior AI researchers or ML engineers.
  • Experience taking a model from research prototype to a system routinely used by other scientists.
  • Open-source release, public benchmark, or tooling contribution used by the community.
  • Ability to work productively in an interdisciplinary environment.
  • Comfort with ambiguity and close collaboration with wet-lab scientists, with the communication skills to explain model behavior and limitations to non-computational colleagues.

Responsibilities

  • Lead generative AI and protein foundation model development, including representation learning, generative protein design, sequence-structure-function modeling, and multimodal biological learning.
  • Set pre-training and fine-tuning strategies, including architecture and model-family selection, training curricula, and evaluation approaches.
  • Design and guide the training lifecycle and scaling approach for LillyPod, ensuring reproducibility, checkpointing, and throughput in partnership with ML infrastructure engineers.
  • Direct confidence and calibration research, treating it as a first-class objective and reducing the gap between model-ranked designs and experimentally validated performance.
  • Investigate underperforming models to identify root causes across architecture, data, and execution, and decide whether to retrain, pivot, or discontinue them.
  • Advance the foundation-model portfolio by establishing success metrics and ensuring progress translates into measurable experimental outcomes.
  • Use proprietary multimodal biological data—including sequence, structure, binding, functional, developability, and other measurements—to create differentiated learning advantages.
  • Recruit, develop, and mentor AI researchers and engineers, while guiding model architecture, experimental design, technical priorities, and research direction.
  • Evaluate external methods, innovations, and collaborations, deciding when to build, adapt, or partner.
  • Communicate technical progress, experimental validation, key learnings, and strategic recommendations to scientific leadership and broader R&D stakeholders.
  • Contribute to publications, external collaborations, and scientific presentations where appropriate.

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