AI / ML Engineer
unitedhealthgroup
Job Description
- Design, develop, and deploy Agentic AI solutions using LLMs, tools, memory, orchestration, and multi-step reasoning workflows
- Build and maintain RAG-based applications using vector databases, embeddings, document ingestion pipelines, retrieval strategies, and prompt engineering
- Develop AI-powered workflow automation solutions to improve operational efficiency and business process intelligence
- Work with frameworks such as Spring AI, LangChain, LangGraph, and related AI orchestration tools
- Integrate AI capabilities into enterprise applications, APIs, microservices, and cloud-native platforms
- Build scalable backend services using Java/Spring Boot and/or Python-based AI frameworks
- Implement prompt engineering, evaluation, guardrails, observability, and monitoring for AI applications
- Work with cloud services on AWS and Azure, including AI/ML services, storage, compute, serverless, containerization, and deployment pipelines
- Implement observability and monitoring for application health, AI workflow performance, model behavior, latency, failures, and usage patterns
- Collaborate with product owners, architects, data engineers, and business stakeholders to understand requirements and deliver AI solutions
- Evaluate emerging AI technologies, LLM providers, model APIs, and open-source frameworks for enterprise adoption
- Ensure AI solutions follow security, compliance, privacy, and responsible AI best practices
- Comply with the terms and conditions of the employment contract, company policies and procedures, and any and all directives (such as, but not limited to, transfer and/or re-assignment to different work locations, change in teams and/or work shifts, policies in regards to flexibility of work benefits and/or work environment, alternative work arrangements, and other decisions that may arise due to the changing business environment). The Company may adopt, vary or rescind these policies and directives in its absolute discretion and without any limitation (implied or otherwise) on its ability to do so