Research Advisor, Computational Chemistry

Role Summary

We are seeking a highly motivated computational chemist to join our team and apply physics-based modeling and cheminformatics to the design of chemically modified oligonucleotide therapeutics. The Lilly Genetic Medicine (LGM) organization is an innovation-focused group dedicated to identifying, developing, and applying cutting-edge technologies to maximize patient benefit. Our Data Science and AI/ML team partners closely with medicinal chemists, biologists, and data scientists across disciplines, playing a central role in molecular design, study design, and data-driven decision-making to accelerate RNA drug discovery. Oligonucleotide therapeutics—including siRNAs, ASOs, and splice-switching oligonucleotides—occupy a unique chemical space between small molecules and biologics. Each position in a therapeutic oligonucleotide can carry distinct sugar, backbone, and base modifications, creating a vast combinatorial design space that is poorly served by conventional computational chemistry tools. This role will bridge molecular simulation, cheminformatics, and machine learning to generate actionable insights that guide the optimization of chemically modified oligonucleotides across Lilly’s RNA therapeutics portfolio.

Responsibilities

• In this role, you will apply and develop computational chemistry methods to understand how chemical modifications influence the structure, stability, target engagement, and pharmacological properties of therapeutic oligonucleotides. You will work closely with medicinal chemists, biologists, and data scientists to translate atomic-level insights into design recommendations that advance portfolio programs and platform capabilities.
• Perform molecular dynamics simulations of chemically modified oligonucleotide duplexes and single-stranded species to characterize the structural and thermodynamic consequences of sugar, backbone, and base modifications
• Apply free energy methods (FEP, thermodynamic integration, MM/PBSA, MM/GBSA) to predict modification-dependent binding affinities, duplex stability, and protein–oligonucleotide interactions
• Develop and validate force field parameters for novel nucleotide analogs using quantum mechanical calculations, enabling rapid computational evaluation of new chemistries emerging from the medicinal chemistry team
• Build and apply cheminformatics descriptors and QSAR/QSPR models adapted for chemically modified oligonucleotides, moving beyond sequence-only representations to capture the full chemical diversity of the modification space
• Collaborate with medicinal chemists and biologists to integrate computational predictions with experimental SAR data, contributing to the identification of optimal modification patterns for on-target potency, selectivity, metabolic stability, and safety
• Contribute to reusable computational workflows, data assets, and modeling platforms that support cross-program learning and integration with the team’s unified machine learning models
• Present findings to cross-functional teams and contribute to scientific strategy discussions, publications, and patent applications

Qualifications

• PhD in computational chemistry, physical chemistry, chemical physics, biophysics, or a closely related field
• Preferred: Demonstrated expertise in molecular dynamics simulation of nucleic acids or chemically modified biopolymers
• Preferred: Experience with free energy calculation methods applied to biomolecular systems
• Preferred: Proficiency in cheminformatics toolkits (RDKit, OpenEye, or equivalent) and/or commercial CADD platforms (Schrödinger, MOE)
• Preferred: Strong programming skills in Python, with experience in scientific computing libraries
• Preferred: Familiarity with machine learning and AI methods applied to molecular sciences, including experience with predictive modeling for molecular properties, chemical optimization, or structure–activity relationships
• Preferred: Excellent written and oral communication skills with ability to present complex computational results to diverse scientific audiences including medicinal chemists and biologists
• Preferred: Experience with high-performance computing and/or cloud-based simulation environments
• Preferred: Demonstrated ability to work collaboratively in cross-functional team environments
• Preferred: Experience with force field parameterization for non-standard nucleotide analogs, including QM-derived charge fitting (RESP, AM1-BCC) and torsion parameter development
• Preferred: Familiarity with quantum chemical methods (DFT, ab initio) for electronic structure analysis of modified nucleotides and their impact on duplex stability and reactivity
• Preferred: Understanding of how chemical modifications influence oligonucleotide secondary structure, folding, and conformational dynamics, including modification-dependent effects on duplex geometry and protein recognition
• Preferred: Experience with machine learning approaches for molecular property prediction, including graph neural networks, molecular language models, or transformer-based architectures applied to chemical or biopolymer data
• Preferred: Familiarity with molecular representations for modified oligonucleotides (HELM, extended SMILES, or similar macromolecular encoding schemes)
• Preferred: Knowledge of oligonucleotide-specific ADME properties, including nuclease-mediated metabolism, plasma protein binding of phosphorothioate backbones, and endosomal escape
• Preferred: Track record of peer-reviewed publications demonstrating expertise in computational chemistry applied to nucleic acids or modified biopolymers
• Preferred: Deep understanding of nucleic acid structure and chemistry, including familiarity with common therapeutic modifications (2’-OMe, 2’-F, 2’-MOE, LNA/cET, phosphorothioate, GalNAc conjugates)
• Preferred: Experience designing computational workflows that integrate with automated experimental platforms and high-throughput screening
• Preferred: Proficiency in Rust or other systems-level languages for performance-critical scientific computing is a plus