Role Description Optum Tech is a global leader in health care innovation. Our teams develop cutting-edge solutions that help people live healthier lives and help make the health system work better for everyone. From advanced data analytics and AI to cybersecurity, we use innovative approaches to solve some of health care’s most complex challenges. Your contributions here have the potential to change lives. Ready to build the next breakthrough? 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. - Design, develop, and deploy production agentic AI systems using OpenAI Agents SDK, Claude Agents SDK, or similar frameworks to power conversational healthcare experiences. - Build and maintain multi-agent orchestration systems that route user requests across specialized Line-of-Business AI agents using Agent-to-Agent (A2A) protocols. - Develop FastAPI backends and Node.js/TypeScript services that integrate LLMs (AWS Bedrock, Vertex AI) with healthcare systems through GraphQL APIs and AWS AppSync. - Implement healthcare-specific guardrails including PII detection/scrubbing, prompt safety, and compliance controls for patient-facing applications. - Deploy containerized AI/ML workloads to AWS (App Runner, ECS, Lambda) with infrastructure-as-code using Terraform and CI/CD pipelines (GitHub Actions). - Collaborate with product and clinical stakeholders to design, evaluate, and optimize agentic AI workflows using quantitative metrics and user feedback. - Monitor LLM application performance, token usage, latency, and user satisfaction in production environments serving millions of health plan members. - Stay current with emerging patterns in generative AI, agent frameworks, and responsible AI practices for healthcare applications. 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. Qualifications - Bachelor’s degree in Computer Science, Data Science, or related field. - 4+ years of hands-on experience with Python or TypeScript or other relevant backend languages such as Java, Node.js. - Experience building RESTful or GraphQL APIs in production environments. - Understanding of LLM fundamentals (prompting, context management, or model integration). - Must be authorized to work in the United States without the need for current or future employer-sponsored visa sponsorship (e.g., H-1B, TN, F-1/OPT, CPT, or other employment-based visa status). Requirements - Production experience with agentic AI frameworks (OpenAI Agents SDK, Claude Agents SDK, LangGraph, or similar). - Hands-on experience with AWS Bedrock, Vertex AI, or Azure OpenAI services. - Experience measuring and improving LLM applications using evaluation frameworks, prompt iteration, or user feedback loops. - Infrastructure-as-code experience with Terraform or CloudFormation. - Experience with AWS services (Lambda, ECS, App Runner, AppSync, DynamoDB). - Healthcare applications, HIPAA compliance, or experience in regulated industries. - Multi-agent systems, agent orchestration, or workflow engines. - FastAPI, Express, or similar backend framework experience. Benefits - Comprehensive benefits package. - Incentive and recognition programs. - Equity stock purchase. - 401k contribution (all benefits are subject to eligibility requirements). 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.

• Owning and driving AI product initiatives e2e from ideation to launch to retention. • Engage with customers to understand their needs and translate them into compelling solutions • Identify new product opportunities and anticipate potential risks and blockers • Collaborate with leaders of other functions to refine product strategy and execute process improvements • Build alignment and drive decision-making across company-wide initiatives • Build impactful relationships and driving collaborative initiatives across functional teams, effectively influencing stakeholders at all levels • Contribute to technical trade-offs, design clean product interfaces and abstractions, and build systems to scale customer, competitor, and market understanding throughout the organization • Work closely with Engineering to drive an efficient R&D process, from leading scrums to coordinating product releases • Collaborate with Customer Success and Go-to-Market teams to ensure that we maximize the product's impact on both customers and our business

• Own Mercury's knowledge infrastructure • Build the knowledge layer on top of Mercury's AI infrastructure • Own the reporting layer • Drive company-wide adoption of standardized systems and practices • Continuously improve how Mercury captures, organizes, and uses knowledge

• Develop, test, and maintain software solutions supporting AI-driven applications. • Write clean, scalable, maintainable, and efficient code. • Collaborate with cross-functional teams to design and deliver high-quality software solutions. • Troubleshoot, debug, and optimize applications for improved performance and reliability. • Participate in code reviews and follow software engineering best practices. • Learn and apply emerging technologies, AI development methodologies, and modern engineering practices. • Contribute to continuous improvement initiatives within software development processes.