Sr Associate AI Full stack Software Engineer

McKesson•Atlanta, GA

11d

About The Position

McKesson is seeking a highly skilled and motivated AI Full Stack Software Engineer to join its team at CMM. The role designs, develops, and deploys end-to-end AI-powered solutions to enhance healthcare products and services, working across front-end interfaces, back-end AI model integration, and data pipelines. The position develops enterprise-quality AI applications and integrates large language models and other AI tools into new and legacy codebases. It also involves building and optimizing AI data pipelines, evaluating and improving model performance and cost, creating AI agents and co-pilot experiences, and documenting work at code and application levels. The engineer collaborates with staff and external stakeholders on large projects and communicates AI concepts to non-technical audiences. Priority will be given to candidates in the Atlanta, Georgia, and Columbus, Ohio metropolitan areas. McKesson is unable to provide sponsorship for this role now or in the future.

Requirements

At least 2 years of experience in software development.
At least 2 years of experience developing AI-enhanced applications using LLMs, voice, image, or speech models.
B.S. degree in Computer Science or a related engineering discipline, or equivalent experience.
Proficiency in AI system evaluation metrics including precision, recall, F1-score, and AUC-ROC, and in MLOps for scalable, cost-efficient AI deployment.
Experience building RAG systems from scratch or with LangChain or LlamaIndex, using vector databases for context-aware LLM applications.
Expertise in managing LLM costs through prompt caching, batching, and quantization, with understanding of token pricing and input/output rates.
Deep understanding of LLM advancements, including GPT-3.5, GPT-4, and o1 or other thinking models, to inform model selection and tuning.
Exceptional analytical skills to extract actionable insights from data.
Experience using AI coding tools such as GitHub Copilot, Cursor, or Codeium/Windsurf.
Proficiency in Python and AI-related Python libraries such as OpenAI, TensorFlow, and PyTorch.
Healthcare domain expertise and ability to translate clinical or business needs into AI solutions.
Proficiency in creating Node.js web applications, such as with Express.js.
Experience with a cloud platform such as AWS, GCP, or Azure.
Effective communication skills for collaboration with technical, DevOps, and product management teams.
Experience with Git, Docker, and Kubernetes.

Responsibilities

Develop and deliver AI-driven enterprise-quality software applications.
Build scalable applications integrating large language models and AI tools such as voice recognition, document parsing, image parsing, text-to-speech, and retrieval-augmented generation into new and legacy codebases.
Design and optimize data pipelines and datasets for AI system development and testing.
Communicate modern AI concepts, including LLMs and vector databases, to non-technical audiences.
Iteratively craft effective prompts to maximize LLM performance and implement prompt-caching strategies.
Maintain prompt libraries and benchmark performance.
Fine-tune and serve GPT-family and Llama models.
Develop AI agents using Semantic Kernel.
Prototype co-pilot experiences and autonomous workflows.
Fully document work at both code and application levels.
Learn and adapt in a changing environment.
Collaborate with staff and outside stakeholders on large projects.
Create solutions and solve complex problems.