Join Optum, a global leader in health optimization, and contribute to improving health outcomes through technology. We are seeking a skilled Java engineer with a passion for AI to design and build scalable, secure Java services. This role offers a unique opportunity to integrate advanced AI features, including LLM-powered workflows, retrieval-augmented generation (RAG), and AI agents, into enterprise applications. Leverage AI coding tools to enhance development speed and efficiency within a culture that champions inclusion, collaboration, and career growth.

This position is ideal for experienced backend engineers who have a proven track record of shipping AI features or are well on their way to doing so. We are looking for individuals who are not just experimenting with AI but are actively applying it to solve complex problems.

Core engineering responsibilities include designing, building, and maintaining high-performance microservices using Java 17+ and Spring Boot. You will develop and utilize secure, observable, and resilient REST, GraphQL, and event-driven APIs (Kafka). You will own features end-to-end, from design and coding to testing, deployment, and production support, ensuring clean, testable code with high quality and test coverage.

AI building entails integrating LLM-powered features into enterprise applications using frameworks like Spring AI or provider SDKs. You will design and manage RAG pipelines, including document chunking, embedding creation, vector store management (pgvector, Azure AI Search, etc.), and retrieval tuning. Building agent workflows with tools and function calls, and versioning/testing prompts with evaluation frameworks are also key. Implementing safeguards for PII/PHI redaction, content filtering, and protection against prompt injection is crucial. Continuous monitoring and tuning of AI features for performance and reliability are expected.

AI-assisted engineering involves utilizing AI coding assistants like GitHub Copilot for daily development tasks and sharing best practices. You will identify opportunities to automate engineering work with AI, such as test generation and incident summarization.

Collaboration and leadership involve working with cross-functional teams to translate business needs into AI solutions. You will mentor other engineers in modern Java and AI development and contribute to shaping team standards for responsible AI, architecture, and engineering practices.

Required qualifications include a Bachelor's or Master's degree in Computer Science, Engineering, or a related field, or equivalent hands-on experience. You should possess 8+ years of hands-on Java experience, with deep knowledge of Java 11/17+, multithreading, collections, and the JVM. Proficiency in microservices, REST APIs, and messaging systems like Kafka is essential. Experience with cloud platforms (AWS preferred, or Azure/GCP), Docker, and Kubernetes is required, along with familiarity in CI/CD practices and test frameworks (JUnit, Mockito, Testcontainers).

A strong foundation in Spring Boot, Spring Cloud, Spring Security, and JPA/Hibernate is necessary. You must be proficient with both SQL and NoSQL databases (PostgreSQL, Oracle, MongoDB, Redis). Hands-on experience building applications with LLMs (GPT, Claude, Llama, Gemini or similar) via APIs is a must. Understanding of responsible AI principles, data privacy, and secure AI design is important, as is a good grasp of embeddings, vector search, RAG, and prompt engineering.

You should comprehend the limitations of LLMs, such as hallucination and non-deterministic output, and know how to design around them. Familiarity with agent concepts like tool/function calling, planning, and multi-agent orchestration is expected. Excellent problem-solving and system design skills, along with clear communication abilities to explain technical concepts to non-technical stakeholders, are vital. A curious mindset and a commitment to staying updated with the rapidly evolving AI field are also key requirements.