Machine Learning Scientist/Sr Scientist – Antibody Property Prediction & Generative Design Full-time

Machine Learning Scientist/Sr Scientist, Antibody Property Prediction & Generative Design

At Lilly, we unite caring with discovery to make life better for people around the world. We are a global healthcare leader headquartered in Indianapolis, Indiana. Our employees around the world work to discover and bring life-changing medicines to those who need them, improve the understanding and management of disease, and give back to our communities through philanthropy and volunteerism. We give our best effort to our work, and we put people first. We're looking for people who are determined to make life better for people around the world.

Lilly TuneLab is an AI-powered drug discovery platform that provides biotech companies with access to machine learning models trained on Lilly's extensive proprietary pharmaceutical research data. Through federated learning, the platform enables Lilly to build models on broad, diverse datasets from across the biotech ecosystem while preserving partner data privacy and competitive advantages. This collaborative approach accelerates drug discovery by creating continuously improving AI models that benefit both Lilly and our biotech partners.

The Machine Learning Scientist/Sr Scientist, Antibody Property Prediction & Generative Design plays an essential role within the TuneLab platform, specializing in antibody and biologic drug development. This position requires deep expertise in antibody engineering, protein design, and immunology, combined with advanced machine learning capabilities in sequence modeling and structure prediction. The role will drive the development of AI models that accelerate antibody discovery, optimization, and developability assessment across the federated network.

Key Responsibilities

• Antibody Property Prediction: Build multi-task learning frameworks specifically for antibody properties including binding affinity, specificity, stability (thermal, pH, aggregation), immunogenicity, and developability metrics from sequence and structural features.
• Antibody Sequence Generation: Develop and implement generative models (transformers, diffusion models, evolutionary models) for antibody design, including CDR optimization, humanization, and affinity maturation while maintaining structural integrity.
• Structure-Aware Design: Integrate structural modeling and prediction (AlphaFold, ESMFold) with generative approaches to ensure generated antibodies maintain proper folding, CDR loop conformations, and epitope recognition.
• Developability Optimization: Create models that simultaneously optimize for multiple developability criteria including expression yield, solubility, viscosity, and post-translational modifications, crucial for manufacturing and formulation.
• Species Cross-Reactivity: Develop approaches to design antibodies with desired species cross-reactivity profiles for preclinical development, learning from cross-species binding data.
• Antibody-Antigen Modeling: Create models for predicting antibody-antigen interactions, epitope mapping, and paratope design, incorporating both sequence and structural information.

Basic Qualifications

• PhD in Computational Biology, Protein Engineering, Immunology, Biochemistry, or related field from an accredited college or university
• Minimum of 2 years of experience in antibody or protein therapeutic development within the biopharmaceutical industry
• Strong experience with protein sequence analysis and structural biology
• Proven track record in machine learning applications to biological sequences
• Deep understanding of antibody structure-function relationships and immunology

Additional Preferences

• Experience with immune repertoire sequencing and analysis
• Publications on antibody design, protein engineering, or therapeutic development
• Expertise in protein language models and transformer architectures
• Knowledge of antibody manufacturing and CMC considerations
• Experience with display technologies (phage, yeast, mammalian)
• Understanding of clinical immunogenicity and prediction methods
• Proficiency in protein modeling tools (Rosetta, MOE, Schrodinger BioLuminate)
• Familiarity with antibody-drug conjugates and bispecific platforms
• Experience with federated learning in biological applications
• Portfolio mindset balancing innovation with practical developability

This role is based at a Lilly site in Indianapolis, South San Francisco, or Boston with up to 10% travel (attendance expected at key industry conferences). Relocation is provided.