Principal Engineer – Scientific Authoring, Frontier AI

Role Overview

• As a Principal Engineer in Frontier AI, you will build intelligent systems that transform how scientists create, analyze, and manage scientific documents.
• You will develop AI-powered tools that assist with manuscript preparation, regulatory submissions, patent applications, and technical documentation, helping researchers focus on science while AI handles the mechanics of scientific communication.
• You will work at the intersection of large language models, scientific knowledge representation, and document engineering to create systems that understand domain context, maintain scientific rigor, and accelerate the authoring lifecycle.
• Design and implement AI agents for scientific document authoring, including literature synthesis, citation management, and figure/table generation.
• Build retrieval-augmented generation (RAG) systems over scientific corpora, ELNs, and internal knowledge bases to ground AI outputs in factual content.
• Develop domain-specific fine-tuning and prompt engineering strategies for chemistry, biology, and pharmacology content.
• Create tools for automated quality checking: scientific accuracy, consistency, formatting compliance, and plagiarism detection.
• Build multi-agent workflows that coordinate literature search, data extraction, drafting, and revision cycles.
• Build production-grade authoring applications with robust software engineering practices (version control, testing, CI/CD).
• Deploy scalable services on cloud-native infrastructure (Kubernetes, AWS) with appropriate guardrails for scientific content.
• Partner with scientists, medical writers, and regulatory teams to integrate AI authoring tools into real workflows.
• Represent Frontier AI in internal forums and external AI/NLP research communities.
• Evaluate external vendors, open-source tools, and academic collaborations for scientific authoring capabilities.

Requirements

• MS + 1 yrs / BS + 2 yrs equivalent experience in Computer Science, Chemical sciences, Bioinformatics, or related discipline with demonstrated scientific domain exposure
• 1-2 years applying NLP/LLM techniques to text generation, summarization, or information extraction (including industry post-doc)
• Hands-on experience with LLM application development (prompt engineering, RAG architectures, agent frameworks)
• Strong software engineering skills: production-quality Python, version control, testing, CI/CD (GitHub portfolio a plus)
• Deep experience with ML/NLP frameworks (PyTorch, HuggingFace, LangChain, LlamaIndex)
• Qualified applicants must be authorized to work in the United States on a full-time basis. Lilly will not provide support for or sponsor work authorization or visas for this role.

Tech Stack

• AWS
• Cloud
• Kubernetes
• Python
• PyTorch

Benefits

• eligibility to participate in a company-sponsored 401(k)
• pension
• vacation benefits
• eligibility for 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)