Advisor, Design Validation & Learning, Biotherapeutics

Eli Lilly and Company • San Diego, CA

21h • Onsite

About The Position

Lilly’s Biotechnology Discovery Research organization develops antibody and peptide therapeutics from concept through clinical development and market. This position is based at the Lilly Biotechnology Center in San Diego and supports the organization’s generative de novo design platform, which combines AI/ML, protein engineering, automation, structural biology, and high-throughput experimentation. The program uses dedicated computing capacity on LillyPod, a company-owned 1,016-GPU NVIDIA Blackwell Ultra SuperPOD.

The Advisor performs rigorous evaluation and validation analyses, translating experimental evidence into insights that improve de novo design capabilities. The role curates datasets, compares computational predictions with experimental outcomes, performs biophysical and physics-based analyses, and collaborates across multidisciplinary teams to identify model and design limitations. It contributes directly to the continuous learning cycle that improves design quality and efficiency.

The position includes evaluating held-out datasets and uncertainty; running molecular simulation, energy-based, and structure-based analyses; building reproducible workflows with design, sample, assay, and experimental metadata; partnering with protein science and automation colleagues on data-generation studies; integrating positive, negative, and ambiguous outcomes into evaluation and training-ready datasets; and communicating findings and recommendations to computational and experimental teams.

Requirements

• Ph.D. in computational biology, biophysics, computational chemistry, bioengineering, chemical engineering, physics, statistics, or a related STEM discipline; alternatively, an M.S. with 3+ years of experience or a B.S. with 5+ years of experience.
• Proficiency in Python and the scientific computing stack, version control, and reproducible analysis.
• Working knowledge of statistics, uncertainty quantification, regression, agreement metrics, calibration, and experimental design.

Nice To Haves

• Hands-on use of OpenMM, GROMACS, Amber, Rosetta, Schrödinger, or related simulation tools.
• Understanding of protein structure and biophysics, including binding, expression, and stability measurements.
• Experience with protein language models, structure prediction, docking, or molecular scoring.
• Experience working with binding and biophysical measurements such as SPR, BLI, thermostability, expression, deep mutational scanning, or other high-throughput biological datasets.
• Experience with antibody or VHH developability.
• Experience with workflow tools such as Snakemake, Nextflow, containers, or scheduled cluster/GPU computing.
• Direct wet-lab experience or close collaboration with experimental scientists.
• Strong written and verbal communication skills, including the ability to communicate quantitative findings, uncertainty, and model limitations to computational and experimental scientists.

Responsibilities

• Assemble held-out datasets; compare computational predictions with experimental outcomes; quantify uncertainty; and identify patterns, limitations, and failure modes to guide model and design improvements.
• Run molecular simulation, energy-based, and structure-based analyses, and evaluate features for stability, aggregation, and developability prediction to determine where these approaches complement ML-based methods.
• Build reproducible data workflows that preserve design, sample, assay, and experimental metadata.
• Partner with protein science and automation colleagues to plan informative data-generation studies and ensure resulting data are suitable for model evaluation, refinement, and subsequent learning cycles.
• Integrate positive, negative, and ambiguous experimental outcomes into evaluation datasets and training-ready data products, and translate findings into recommendations for subsequent model and design iterations.
• Clearly present findings, uncertainty, model limitations, and experimental evidence to computational and experimental teams, translating results into actionable recommendations.

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, such as 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.

What This Job Offers

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