Requisition Number: 2359757 Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start Caring. Connecting. Growing together. You'll enjoy the flexibility to work remotely* from anywhere within the U.S. as you take on some tough challenges. For all hires in the Minneapolis or Washington, D.C. area, you will be required to work in the office a minimum of four days per week. Primary Responsibilities: - Design and build AI-powered features using NLP/LLMs and classical ML for provider chat and voice workflows - Deliver end to end: data preparation, modeling/experimentation, evaluation, API integration, deployment, and monitoring in cloud environments - Implement responsible AI guardrails (content safety, PHI/PII controls, prompt hygiene, evaluation suites) and collaborate with governance/review partners - Develop and maintain web services and APIs that expose ML capabilities; write clear documentation and runbooks - Apply MLOps practices (CI for ML, model registry, reproducible experiments) and contribute to on call/operational support with mentorship - Collaborate with product, architecture, security, data, and platform teams to align with enterprise standards and deliver measurable outcomes - Continuously improve code quality, test coverage, latency, reliability, and cost per inference - Design, develop, and deploy AI-powered solutions using no-code, low-code, and advanced platforms, translating business needs into scalable applications that enhance products, workflows and decision-making You'll be rewarded and recognized for your performance in an environment that will challenge you and give you clear direction on what it takes to succeed in your role as well as provide development for other roles you may be interested in. Required Qualifications: - 1+ years of total software engineering experience - 1+ years of experience with Python and/or Java programming - 1+ years of experience building and integrating model-backed APIs/services (Python, Node, or Java) into production systems - 1+ years of hands-on experience in AI/ML (e.g., NLP, GenAI, predictive modeling, or recommendation systems) - 1+ years of experience working with AWS cloud and core components (containers/serverless, IAM basics, storage/networking fundamentals, logging/metrics) - 1+ years of experience implementing security, access control, monitoring/alerting, and foundational resiliency/DR concepts for cloud applications - 1+ years of experience with version control, code reviews, automated testing, and CI/CD Preferred Qualifications: - Bachelors degree in Computer Science/related fields or equivalent experience - Exposure to healthcare data/processes *All employees working remotely will be required to adhere to UnitedHealth Group's Telecommuter Policy Pay is based on several factors including but not limited to local labor markets, education, work experience, certifications, etc. In addition to your salary, we offer benefits such as, a comprehensive benefits package, incentive and recognition programs, equity stock purchase and 401k contribution (all benefits are subject to eligibility requirements). No matter where or when you begin a career with us, you'll find a far-reaching choice of benefits and incentives. The salary for this role will range from $72,800 to $130,000 annually based on full-time employment. We comply with all minimum wage laws as applicable. Application Deadline: This will be posted for a minimum of 2 business days or until a sufficient candidate pool has been collected. Job posting may come down early due to volume of applicants. At UnitedHealth Group, our mission is to help people live healthier lives and make the health system work better for everyone. We believe everyone-of every race, gender, sexuality, age, location and income-deserves the opportunity to live their healthiest life. Today, however, there are still far too many barriers to good health which are disproportionately experienced by people of color, historically marginalized groups and those with lower incomes. We are committed to mitigating our impact on the environment and enabling and delivering equitable care that addresses health disparities and improves health outcomes - an enterprise priority reflected in our mission. UnitedHealth Group is an Equal Employment Opportunity employer under applicable law and qualified applicants will receive consideration for employment without regard to race, national origin, religion, age, color, sex, sexual orientation, gender identity, disability, or protected veteran status, or any other characteristic protected by local, state, or federal laws, rules, or regulations. UnitedHealth Group is a drug - free workplace. Candidates are required to pass a drug test before beginning employment.

• Design and build AI systems behind real, production-grade applications • Own the full path from idea to deployment, including evaluation and observability • Create multi-step agents and tool-using LLM systems • Integrate AI workflows into business-critical environments • Collaborate with engineers, strategists, and designers

• Design and build agentic AI systems that facilitate conversational workflows for seller enablement • Develop a chat-based seller assistant that: • Answers seller questions using enterprise data • Provides insights on ordering, pricing, and customer behavior • Generates pre-visit one-pagers to guide sales conversations • Integrate large language models (e.g., Claude, ChatGPT) with internal data sources and APIs • Apply prompt engineering, context engineering, and agent orchestration techniques to improve reliability and usefulness • Build and evolve the platform using LangChain and LangGraph (initially in Python) • Design persistence and data access layers using Mongo or other data stores • Collaborate closely with product, analytics, and engineering partners to shape both technical direction and use cases • Serve as a champion for modern AI coding assistant tools (e.g., Cursor) within the team • Help define standards and best practices as this AI capability scales

Role Description AI Engineer / Architect with deep expertise in designing and implementing advanced AI systems, particularly those leveraging Agentic RAG (Retrieval-Augmented Generation). The ideal candidate will combine strong technical skills in AI/ML engineering with architectural vision, enabling scalable, intelligent, and context-aware solutions. This role requires hands-on development, system design, and collaboration across multidisciplinary teams to deliver cutting-edge AI capabilities. Responsibilities - Architect and implement Agentic RAG solutions, integrating retrieval mechanisms with generative models to enhance accuracy, adaptability, and contextual relevance. - Design and optimize AI pipelines for data ingestion, indexing, retrieval, and generation, ensuring scalability and performance. - Develop reusable AI components and frameworks that support agent orchestration, multi-step reasoning, and dynamic workflows. - Collaborate with data engineers, ML scientists, and product teams to align AI solutions with business objectives and operational requirements. - Evaluate and integrate vector databases, embeddings, and retrieval strategies to maximize system efficiency. - Conduct experiments, benchmarking, and performance tuning of RAG-based architectures. - Define and enforce best practices for AI system design, including security, compliance, and ethical considerations. - Stay current with emerging trends in agentic AI, LLM orchestration, and retrieval-augmented architectures. Qualifications - Bachelor's or Master's degree in Computer Science, Data Science, AI/ML, or related field. - 5+ years of experience in AI engineering or architecture, with proven expertise in RAG implementations. - Strong proficiency in Python, C#, or Java, with hands-on experience in ML frameworks (TensorFlow, PyTorch, Hugging Face). - Experience with vector databases (e.g., Pinecone, Weaviate, Milvus) and embedding models. - Solid understanding of LLM orchestration frameworks (LangChain, Semantic Kernel, or equivalent). - Knowledge of cloud platforms (Azure, AWS, GCP) and containerization (Docker, Kubernetes). - Strong problem-solving skills and ability to design scalable, production-ready AI systems. - Excellent communication skills for presenting architectural solutions to both technical and executive stakeholders. Preferred Skills - Experience with agent orchestration tools and multi-agent systems. - Familiarity with knowledge graphs, semantic search, and hybrid retrieval methods. - Background in DataOps or MLOps, ensuring smooth deployment and monitoring of AI systems. - Bilingual communication (Spanish/English) is a plus for global collaboration. Requirements - Fluent Advanced (96-100%) - Remote