AI full stack Engineer

McKesson is an impact-driven healthcare company delivering products, services, and insights to make quality care more accessible and affordable. The AI Full Stack Software Engineer will design, develop, and deploy end-to-end AI-powered healthcare solutions across front-end interfaces, back-end model integrations, and data pipelines.

Responsibilities:

• Develop and deliver AI-driven enterprise quality software applications
• Build scalable applications integrating Large Language Models and other AI tools (e.g. voice recognition, document parsing, image parsing, text to speech, RAG) into new and legacy codebases
• Design and optimize data pipelines and datasets for AI system development and testing
• Communicate modern AI concepts (LLMs, vector databases etc.) to non-technical audiences
• Iteratively craft effective prompts to maximize LLM performance and implement prompt caching strategies
• Maintain prompt libraries & benchmark performance
• Fine-tune & serve GPT-family, Llama
• Develop AI agents Semantic Kernel
• Prototype co-pilot experiences & autonomous workflows
• Fully document all work at both the code level and application level
• The ability to learn and adapt in a changing environment
• Collaborate with other staff and outside stakeholders on large projects
• Must be passionate about creating solutions and solving complex problems

Requirements:

• Minimum 4+ years of experience in Software development
• B.S. degree in Computer Science or related engineering discipline, or equivalent experience
• Minimum 4+ years of experience in developing AI-enhanced applications using LLMs, voice, image, or speech models
• Proficiency in Python and AI related python libraries such as openai, tensorflow, pytorch
• AI System Evaluation & Optimization: Proficient in sensitivity metrics (precision, recall, F1-score, AUC-ROC) and MLOps for scalable, cost-efficient AI deployment
• RAG Development: Skilled in building RAG systems from scratch or with LangChain/LlamaIndex, using vector databases for context-aware LLM applications
• Experience using AI coding tools (e.g. Github Copilot, Cursor, Codeium/Windsurf)
• LLM Cost Optimization: Expert in managing LLM costs (token pricing, input/output rates) via prompt caching, batching, and quantization
• LLM Knowledge: Deep understanding of LLM advancements (GPT-3.5 vs GPT-4 vs o1/”thinking” models) for informed model selection and tuning
• Exceptional analytical skills to extract actionable insights from data
• Healthcare Domain Expertise, Translate clinical/business needs into AI solutions
• Proficiency in creating Node.js web apps (e.g. Express.js)
• Experience with cloud (AWS/GCP/Azure)
• Effective communication skills to collaborate with technical, DevOps and product management teams
• Experience with Git, Docker, and Kubernetes