Advisor - Applied Deep Learning Architect

Lilly • San Diego, CA

1d • Hybrid

About The Position

Lilly’s Biotechnology Discovery Research (BioTDR) organization has a track record for delivering novel biotherapeutic medicines advanced into clinical research in key areas of unmet medical needs, across a variety of therapeutic areas. Integrating biology with innovative scientific capabilities in protein discovery, engineering and computational sciences, we are committed to delivering next wave of biomedicines. We are seeking an AI Theory a deep learning Scientist to join our AI/ML team embedded in BioTDR.
This position is based at the Lilly Biotechnology Center in San Diego or in our HQ in Indianapolis, IN (San Diego preferred), situated at the intersection of Computational Science, Protein Bioscience, High Throughput Experimentation/Lab Automation, Protein Engineering, and Information Technology. In this role, you will be responsible for rigorously analyzing and contributing to the design decisions of deep learning architectures for protein design and engineering in the large molecule and peptide space. You will bring deep learning expertise to the challenge of designing, evaluating, and advancing next-generation models for in-silico drug discovery with new, differentiated capabilities. Your work will span multi-modal model design, and feature integration of protein molecular dynamics. Collaborating closely with a cross-functional team, you will contribute to the discovery of novel biotherapeutic candidates across antibodies, peptides, multi-specifics, and bio-conjugates.

Requirements

• Ph.D. in Computer Science, Artificial Intelligence, Theoretical Computer Science, Applied Mathematics, Computational Biology, Physics, or a related field.
• Strong expertise in modern deep learning architectures, including transformers, diffusion models, flow-matching networks, variational autoencoders, and graph neural networks.
• Proficiency in Python and modern AI/ML frameworks (PyTorch or TensorFlow).
• Familiarity with good software engineering practices including Git version control, code review, testing, and documentation.

Nice To Haves

• 1-3 years of industry experience in development and deployment of Novel Deep Learning Architecture
• Familiarity with protein engineering, protein sequence and structure representation, protein language models (e.g., ESM, AbLang), generative protein models (RFDiffusion, Boltz, Chai, etc.) or related biomolecular ML.
• Experience applying ML to antibody, nanobody, or peptide design is strongly preferred.
• Experience with multi-modal architectures that jointly model sequence, structure, and functional annotations, and that fuse molecular representations across different molecule modalities (e.g., protein-peptide, protein–ligand, protein–small molecule).
• Protein structure understanding; experience.
• Experience integrating molecular dynamics simulations, force-field representations, or physics-based priors into machine learning models for molecular design or optimization.
• Experience with distributed training, GPU-accelerated workflows, and writing performant code for large-scale model training and inference.
• Prior exposure to experimental biologics workflows (phage display, yeast display, directed evolution) that informs practical design constraints is a plus.
• Demonstrated history of high-impact publications in top-tier machine learning, AI, or computational biology venues.
• Strong oral and written communication skills, with the ability to effectively communicate technically challenging concepts and ideas with team members across expert disciplines.

Responsibilities

• Design, implement, and evaluate generative and predictive deep learning architectures—transformers, diffusion models, flow-matching models, and graph neural networks.
• Share actionable strategies and drive architectural decisions to improve the performance of foundational models for biologics drug discovery.
• Develop multi-modal embeddings that unify protein sequence, structure, and molecular fingerprints, researching novel tokenization schemes and fusion mechanisms that improve both generation quality and property prediction.
• Research approaches for jointly modeling proteins and small molecules within the foundational architecture, enabling applications to ADCs, antibody–peptide conjugates, T-cell engagers, and other multi-component biotherapeutic formats.
• Partner with internal MD scientists to integrate physics-based priors, molecular dynamics, and energy-aware learning objectives into model training to ground generative outputs in physical reality and improve the developability of designed molecules across complex modalities.
• Stay at the frontier of AI/ML and computational biology research; identify high-impact directions that advance the foundational model platform and translate them into actionable strategies for the team.
• Educate and transfer knowledge to other domain experts effectively to drive cross-functional collaboration on cutting-edge science.

Benefits

• company bonus (depending, in part, on company and individual performance)
• company-sponsored 401(k)
• pension
• vacation benefits
• medical, dental, vision and prescription drug benefits
• flexible benefits (e.g., 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 (e.g., 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