Principal Software Engineer-Agentic AI

About the role

The Elsevier Healthcare Education (EHE) Data and Content Software Engineering team is responsible for building and maintaining scalable content ingestion pipelines that power critical health education products. Our work enables flagship platforms such as Sherpath and HESI, ensuring high-quality, reliable, and timely delivery of educational content to learners and educators worldwide. We focus on developing robust, efficient systems that transform and manage complex data, supporting innovation across Elsevier’s health education ecosystem.

Requirements

• Agentic AI & Advanced Tooling Experience designing, building, or integrating agentic AI systems (e.g., autonomous workflows, multi-step reasoning agents, AI copilots).
• Hands-on experience with LLMs and orchestration frameworks (e.g., LangChain, OpenAI APIs, or similar).
• Ability to design tool-augmented agents (function calling, retrieval-augmented generation, memory systems, planning/execution loops).
• Experience with prompt engineering, evaluation, and guardrails for production-grade AI systems.
• Understanding of AI system architecture, including latency, cost optimization, observability, and reliability of agent workflows.
• Familiarity with vector databases, embeddings, and retrieval systems.
• Experience integrating AI capabilities into enterprise systems and developer workflows.
• Knowledge of responsible AI practices, including safety, bias mitigation, and governance.

Responsibilities

• Lead the design and development of agentic AI systems
• Architect and deliver autonomous workflows, multi-step reasoning agents, and AI copilots that solve complex business problems across the organization.
• Define and implement LLM-powered architectures
• Build and optimize tool-augmented agents
• Develop agents that effectively utilize function calling, retrieval-augmented generation (RAG), memory systems, and planning/execution loops to perform reliable, context-aware tasks.
• Create standardized approaches for prompt design, testing, benchmarking, and continuous improvement to ensure high-quality outputs in production environments.
• Implement production-grade guardrails and safety mechanisms
• Drive AI system performance and reliability
• Optimize latency, throughput, and cost efficiency of AI systems while ensuring high availability, observability, and fault tolerance across agent workflows.
• Architect solutions using embeddings, vector databases, and hybrid search techniques to enable accurate, scalable knowledge retrieval.
• Integrate AI capabilities into enterprise platforms
• Embed AI services into existing products, APIs, and developer workflows, ensuring seamless interoperability with enterprise systems and data sources.
• Partner with product, data, and engineering leaders to define AI roadmaps, prioritize initiatives, and align solutions with business objectives.
• Champion responsible AI practices
• Ensure systems adhere to standards for fairness, bias mitigation, transparency, and governance, while meeting regulatory and organizational compliance requirements.
• Mentor and elevate engineering teams
• Provide technical leadership, guide architectural decisions, and mentor engineers in building scalable, maintainable AI systems.
• Continuously evaluate emerging technologies
• Stay at the forefront of advancements in AI/ML, agent frameworks, and tooling, and drive adoption of innovations that create competitive advantage.

Pay

$115,400 - $192,300 U.S. National Base Pay Range. Geographic differentials may apply in some locations to better reflect local market rates.

Schedule

N/A

Benefits

Click here to access benefits specific to your location.