Advisor - Generative Design & Optimization, Biotherapeutics
About The Position
Lilly’s Biotechnology Discovery Research organization is expanding computational capabilities at the Lilly Biotechnology Center in San Diego to build an integrated de novo design platform for therapeutic antibodies and other biotherapeutics. The platform brings together AI/ML, protein engineering, automation, structural biology, and high-throughput experimentation to generate, rank, and optimize molecules, with experimental validation informing a continuous learning cycle. The program has dedicated capacity on LillyPod, a 1,016-GPU NVIDIA Blackwell Ultra SuperPOD. This hands-on research role contributes to Lilly’s de novo design pipeline. Building on generative protein foundation models, the Advisor implements, tests, and improves conditioning, sampling, optimization, and scoring methods that make generative capabilities a reliable design engine for antibody and VHH discovery. The role owns key technical problems, contributes new ideas, and translates AI advances into measurable impact on therapeutic discovery. The Advisor works with multidisciplinary computational and experimental teams and supports scientific communication and validation activities.
Requirements
- Ph.D. in computer science, computational biology, bioengineering, chemistry, physics, or a related STEM field; or an M.S. with at least 2 years of relevant experience; or a B.S. with at least 3 years of relevant experience.
- Hands-on experience applying machine learning to sequence, structure, molecular, biological, or other scientific data.
- Proficiency in Python and a modern deep learning framework.
- Experience using GPU computing.
Nice To Haves
- Hands-on experience with active learning, Bayesian optimization, multi-objective optimization, quality-diversity methods, or related optimization approaches.
- Experience curating structural, sequence, or assay datasets, including held-out dataset creation, structure-aware evaluation, and leakage assessment.
- Experience with generative models for proteins or other molecules, including diffusion models, flow-matching, autoregressive sequence models, or related approaches.
- Exposure to physics-based or structure-based scoring methods, such as Rosetta, FoldX, docking methodologies, or energy-based calculations.
- Working knowledge of protein structures, antibodies, VHHs, or related therapeutic modalities.
- Experience working with experimental scientists and biological assay data.
- Strong written and verbal communication skills, including the ability to explain model behavior, design tradeoffs, and limitations to non-computational colleagues.
- Ability to work productively in a multidisciplinary environment spanning computational science, protein engineering, structural biology, automation, and experimental biology.
Responsibilities
- Implement, test, and compare conditioning, guidance, restraint, and sampling methods for target-specific antibody and VHH designs.
- Develop, evaluate, and refine molecular-generation, optimization, and candidate-selection approaches when existing methods do not meet design objectives.
- Implement and evaluate iterative refinement and optimization methods, assessing design quality relative to computational and experimental cost.
- Apply, evaluate, and improve scoring methods that combine learned and physics-based signals to rank designs by affinity, epitope, diversity, developability, and other relevant criteria.
- Prepare, quality-check, version, and document sequence, structure, and assay datasets for design and evaluation.
- Maintain held-out datasets, perform leakage checks, and compare design methods using fit-for-purpose metrics.
- Prepare design sets for experimental testing with the Active Learning & Design Validation team, track outcomes, and feed results into method comparisons and future design iterations.
- Collaborate with foundation model researchers, design validation scientists, data scientists, protein scientists, structural biologists, and automation colleagues to improve design performance and accelerate discovery.
- Present findings clearly to computational and experimental teams and contribute to publications, external presentations, and scientific communications where appropriate.
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.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
Ph.D. or professional degree
