Lilly Small Molecule Discovery is looking to accelerate molecule discovery by building highly optimized foundational platforms, streamlining lab operations through advanced technologies and data connectivity, and intentionally investing in novel technologies and capabilities. The Frontier AI team aims to fuse scientific AI, lab automation, and unified data platforms to autonomously design, run, and refine experiments, thereby accelerating molecule discovery.
Requirements
- Strong background in organic chemistry (particularly in synthesis or methods development), and/or mechanism and reaction modeling.
- Experience with reaction informatics and retrosynthesis algorithms.
- Proficiency in Python and one or more cheminformatics toolkits (e.g., RDKit, CGRtools).
- Experience with machine learning and deep learning frameworks (e.g., scikit-learn, PyTorch, TensorFlow).
- Hands-on experience with HTE platforms or automated chemistry systems.
- Familiarity with eLN systems and AI-to-lab integration.
- Demonstrated ability to work across interdisciplinary teams and contribute to tool deployment or platform development.
Responsibilities
- Refine deep learning models (e.g., graph-based transformers) for reaction product and condition prediction.
- Curate and integrate reaction datasets from internal sources to train and benchmark models.
- Evaluate external models (e.g., RPBP, NERF) for relevance and applicability across reaction classes.
- Develop tools and APIs to integrate predictive models with high-throughput experimentation (HTE) platforms.
- Enable data-driven reaction condition optimization and parallel library synthesis through automation-friendly workflows.
- Collaborate with the Agentic AI systems to prototype eLN-to-lab automation agents.
- Apply cheminformatics techniques (reaction encoding, fingerprinting, condition clustering) to support model interpretation and experimental planning.
Other
- Ph.D. in organic chemistry, cheminformatics, computational chemistry, or related field (degree must be awarded by start date).
- Work cross-functionally with medicinal chemistry, automation, and AI/ML teams.
- Present findings through internal presentations, external publications, and conferences.
- This position is not permanent. It is for a fixed duration of 2 years, with the potential to extend to a maximum of 4 years.
- The physical demands of this job are consistent with an office and lab environment.
