Senior Applied AI Engineer

Senior Applied AI Engineer page is loaded## Senior Applied AI Engineer locations:
Remote New York:
Louisville, KY:
Washington, DC:
Frisco, TX:
Tampa, FLtime type:
Full time posted on:
Posted Todayjob requisition :
R-406185#
** Become a part of our caring community and help us put health first
** The Enterprise AI organization at Humana is a pioneering force, driving AI innovation across our Insurance and Center Well business segments. By collaborating with world-leading experts, we are at the forefront of delivering cutting-edge AI technologies for improving care quality and experience of millions of consumers. Our goal is to create safe AI solutions that will revolutionize and improve healthcare experience and outcomes for our customers.
We are actively seeking top talent to join us in shaping the future of healthcare through AI excellence. Join our rapidly expanding team of dedicated product managers, data scientists, engineers, policy experts, and business leaders as we work together to build impactful and beneficial AI systems.

At Humana, we are strategically leveraging advanced artificial intelligence technologies to fundamentally transform healthcare delivery, enhance member experiences through personalization and intelligent automation, and improve clinical outcomes through data-driven insights. We are seeking a talented Senior Applied AI Engineer to design and implement production-grade AI solutions that deliver measurable business value, with a strong emphasis on Generative AI technologies, sophisticated Retrieval-Augmented Generation (RAG) systems, and intelligent agent architectures that can automate complex workflows and provide personalized assistance.

This critical role focuses on the practical application of cutting-edge AI capabilities within secure and compliant healthcare systems that handle sensitive protected health information. The successful candidate will build robust AI-powered features that deliver measurable impact on member satisfaction, operational efficiency, and clinical quality, while ensuring reliability through comprehensive testing and monitoring, following ethical AI practices that prevent bias and ensure fairness, and maintaining strict alignment with healthcare regulatory standards including HIPAA privacy and security requirements.
* Key Responsibilities
** Design and implement sophisticated AI-powered application features using modern AI SDKs and orchestration frameworks (e.g., Lang Chain, Llama Index, Semantic Kernel), incorporating best practices for prompt engineering, context management, error handling, and user experience design to create AI capabilities that seamlessly integrate into healthcare applications and deliver intuitive, helpful experiences for members and healthcare providers.
* Build and deploy comprehensive RAG pipelines including generation of high-quality embeddings using state-of-the-art models, implementation and optimization of vector databases (e.g., Pinecone, Weaviate, Chroma) for efficient similarity search, sophisticated retrieval optimization techniques such as hybrid search and re-ranking, and integration of retrieved context with large language models to generate accurate, contextually relevant responses.
* Develop scalable backend APIs in Python using modern frameworks (e.g., FastAPI, Flask) to serve AI-enabled healthcare applications with low latency and high throughput, implementing proper authentication and authorization, comprehensive error handling and logging, rate limiting and resource management, and monitoring capabilities that enable operational teams to maintain service quality.
* Integrate advanced AI capabilities into full-stack web applications, working with modern frontend frameworks (e.g., React, Vue) to create responsive user interfaces that leverage AI features effectively, implementing streaming responses for improved perceived performance, handling asynchronous AI operations gracefully, and providing appropriate user feedback and error messages.
* Optimize prompts through systematic experimentation and evaluation, implement sophisticated context management strategies to maximize information density while respecting token limits, and develop token usage optimization strategies including prompt caching, model selection based on task requirements, and batching where appropriate to control costs while maintaining qualit
* Implement comprehensive evaluation frameworks including both automated metrics (e.g., relevance scores, semantic similarity) and human evaluation workflows, develop and deploy guardrails to prevent harmful outputs and ensure responses remain within appropriate boundaries, and establish monitoring systems that track AI system performance, detect anomalies, and alert teams to potential issues.
* Collaborate closely with product managers to translate healthcare use cases into technical requirements, work with data teams to ensure access to high-quality training and retrieval data, partner with clinical subject matter experts to…