GenAI Engineer – Healthcare AI & LLM Orchestration

Cardinal Health; Jackson (MS); On-site; USD 96,000 - 151,000; Full time

Benefits offered by this job

Medical, dental and vision coverage

Paid time off plan

Health savings account (HSA)

401k savings plan

Access to wages before pay day with my

Flexible spending accounts (FSAs)

Disability coverage

Work-Life resources

Paid parental leave

Healthy lifestyle programs

Job summary

Cardinal Health is seeking an AI Engineer to design, deploy, and scale GenAI-powered applications across healthcare operations and enterprise workflows. You will work with LangChain, LangGraph, and LlamaIndex to build production-grade AI services, with a focus on secure, compliant AI in regulated environments.

You will partner with product, engineering, and analytics teams to ensure scalable AI platforms, cloud-native deployment (Azure/GCP), and governance across the lifecycle.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field preferred.
• 5+ years of professional software engineering experience, with strong proficiency in Python and any of the one programming language such as Java / .Net /C# etc preferred.
• 2+ years of hands-on experience building GenAI / LLM-based applications in real-world or enterprise environments.
• Experience designing and implementing agentic or multi-step AI workflows using orchestration frameworks such as LangGraph or similar.
• Strong understanding of retrieval pipelines, embeddings, vector databases, prompt engineering, and LLM APIs.
• Experience deploying AI solutions in cloud environments (Azure and/or GCP).
• Familiarity with secure application development and enterprise integration patterns.
• Experience working in healthcare, life sciences, pharmacy services, or regulated industries preferred.
• Knowledge of HIPAA, PHI data handling, and secure AI design in compliance-driven environments preferred.
• Exposure to responsible AI practices, model monitoring, and governance in enterprise settings preferred.

Responsibilities

• Design, prototype, and deploy Generative AI applications using techniques such as Retrieval-Augmented Generation (RAG), prompt engineering, fine-tuning, and vector search.
• Build and maintain Python-based APIs and software components to support AI services and ensure scalable, production-grade solutions.
• Develop multi-step, agentic workflows for reasoning, task execution, and orchestration using frameworks such as LangChain, LangGraph, and LlamaIndex.
• Integrate AI capabilities into healthcare and pharmacy services workflows, including case management, program operations, analytics, and internal knowledge systems.
• Deploy, monitor, and optimize GenAI models and pipelines using cloud-native tooling, orchestration frameworks, and MLOps best practices.
• Contribute to the AI platform and reference architecture across cloud environments, including Microsoft Azure and Google Cloud Platform (GCP).
• Collaborate with cross-functional teams to ensure AI solutions meet security, privacy, and compliance requirements (e.g., HIPAA, PHI handling, responsible AI principles).
• Document designs, patterns, and best practices to support enterprise reuse and long-term platform sustainability.
• Evaluate vendor solution architecture, APIs, data flows, identity and access controls, security, scalability, interoperability, and operational supportability.
• Participate in technical discovery and proof-of-concept activities, document findings and trade-offs, and provide recommendations for vendor selection, integration approach, and implementation readiness.

Skills

Python

Java

GenAI

Software engineering

Education

Bachelor’s or Master’s degree in Computer Science or related field

Tools

LangChain

LangGraph

LlamaIndex

Azure

GCP

Job description

Cardinal Health is seeking an AI Engineer to design, deploy, and scale GenAI-powered applications across healthcare operations and enterprise workflows. You will work with LangChain, LangGraph, and LlamaIndex to build production-grade AI services, with a focus on secure, compliant AI in regulated environments.

You will partner with product, engineering, and analytics teams to ensure scalable AI platforms, cloud-native deployment (Azure/GCP), and governance across the lifecycle.