Scientific Lead, Generative AI Engineer, Applied Intelligence for Discovery

Sourced from jobs.biospace.com

Eli Lilly is building a generative AI foundation for drug discovery. As a Generative AI Engineer on the Applied Intelligence for Discovery team, you will design and build RAG pipelines, text-to-SQL systems, and agentic workflows to enable scientists to query petabyte-scale data via natural language. This role focuses on developing production-grade AI systems and evaluation frameworks to accelerate biomedical research.

• Design, build, and optimize RAG pipelines over internal scientific documents.
• Build hybrid retrieval systems combining vector search with structured metadata and knowledge graphs.
• Build and optimize text-to-SQL systems over complex omics databases.
• Develop schema documentation and gold-standard question/SQL pairs.
• Implement multi-step reasoning approaches (chain-of-thought, self-correction, Reflexion loops).
• Design agentic AI workflows that chain database queries, bioinformatics tools, and visualization.
• Evaluate and integrate orchestration frameworks (LangGraph, CrewAI).
• Build evaluation frameworks measuring accuracy, reliability, and scientific validity.

• PhD in Computer Science, Data Science, or related field with 0-3+ years of experience building production LLM systems, or MS with 5+ years.
• Strong software engineering skills in Python.
• Deep familiarity with the modern LLM ecosystem (embedding models, vector databases, orchestration frameworks).
• Experience designing evaluation frameworks for LLM systems.
• Familiarity with cloud computing (AWS preferred), Docker, and CI/CD.

• Experience in pharmaceutical, biotech, or life sciences environments.
• Familiarity with biomedical data types (omics, clinical, molecular) or scientific databases.
• Experience with MLOps/LLMOps tooling.
• Knowledge of biomedical ontologies (Gene Ontology, MeSH, ChEBI).
• Experience building for regulated environments requiring auditability and explainability.