Lead AI/ML Engineer: Hybrid in Minnesota or DC, Remote elsewhere

UnitedHealth Group•Eden Prairie, MN

6d•Hybrid

About The Position

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. Come build the AI foundation behind SGS, a modern platform where multi agent systems can reason, plan, and safely connect to enterprise tools to turn conversations, documents, and network signals into action. In this role, you will own the architecture for the capabilities customers feel every day, including real time voice translation, voice based assessments, and call quality audits that help teams respond faster and follow the right procedures. You will also advance Document AI and our Virtual Investigator to accelerate intake, surface risk early, and turn complex investigative questions into clear, explainable answers. On the fraud side, you will combine real time ML with graph analytics to detect emerging hotspots, uncover collusive networks, and stop improper payments before they happen, then translate that intelligence into AI generated insights and KPI visibility leaders can use immediately. You will set the technical direction for orchestration and governance on Azure, raise engineering standards across product lines, and mentor a globally distributed team that ships to production. If you want deep ownership, high stakes impact, and the chance to define how agentic AI operates at scale, you will thrive here. 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. 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.

Requirements

Bachelor’s degree or higher in Computer Science, Engineering, or related field, or equivalent professional experience
8+ years building production software, including 3+ years as a technical lead for AI or ML product development (ownership from design through launch)
5+ years professional Python experience and hands on use of ML or NLP libraries such as PyTorch, Hugging Face, or scikit learn, including deploying models or pipelines to production
3+ years hands on building and operating Spring Boot microservices in production, including API design, automated testing, CI/CD, and on call or incident participation
Agentic and LLM systems: Proven shipped at least one LLM based system to production that uses tool calling or function calling to interact with external services or enterprise APIs, with defined evaluation and monitoring
RAG and vector search: Proven built and shipped retrieval augmented generation or semantic search solutions using vector search, embeddings, and external knowledge integration (for example Azure Cognitive Search or comparable tooling)
Azure architecture: Proven built and deployed production workloads on Azure, using multiple services such as Azure OpenAI, Azure Functions, Event Hubs, Cognitive Search, and Cosmos DB, with security, observability, and cost considerations

Nice To Haves

LLM evaluation and regression testing: Experience building automated evaluation harnesses for LLM and agent workflows, including golden datasets, offline and online testing, and measurable quality metrics (for example task success rate, groundedness, or human review agreement)
Responsible AI and adversarial testing: Hands on experience with prompt injection and data exfiltration testing, safety reviews, and implementing guardrails to reduce hallucinations and unsafe outputs in production
Production observability for agents: Proven implemented end to end monitoring for agentic systems, including distributed tracing, tool call success rates, latency and error budgets, and token and cost telemetry with actionable alerting
Security for tool calling and AI systems: Proven designed secure patterns for tool enabled agents, including least privilege access, secrets management, and policy based controls for tool/API execution (for example OAuth scopes, managed identity, and audit logging)
Platform scale and efficiency: Proven ability to optimize LLM or voice system performance and cost using techniques such as caching, batching, streaming responses, rate limiting, model routing, and fallback strategies

Responsibilities

Lead AI System Design: Architect and evolve our multi-agent AI platforms, enabling agents to reason, plan, and interact with external tools via LLMs and modular service layers
Technical Ownership: Define standards, best practices, and technical vision for AI orchestration across product lines including voice agents, fraud detection, and agentic workflows
Multi-Agent Frameworks: Guide adoption of frameworks like LangChain, AutoGen, and Semantic Kernel; integrate emerging protocols such as Model Context Protocol (MCP) to scale tool and agent interoperability
AI Interface Innovation: Lead the design of agentic user experiences, enabling LLMs to act as intelligent interfaces to enterprise tools and APIs
Voice AI Strategy: Architect full-stack voice agent pipelines - from ASR and multi-turn dialogue to TTS and telephony integrations (SIP, Twilio, etc.)
ML & Fraud Systems: Oversee development and deployment of ML models for fraud and anomaly detection, emphasizing scalability, explainability, and real-time responsiveness
Cloud-Native Engineering: Lead AI/ML system deployment using Azure OpenAI, Azure Functions, Event Hubs, Cognitive Search, Cosmos DB, and other cloud-native tools
Mentorship & Delivery: Guide senior and junior engineers, lead architecture reviews, and drive cross-team technical delivery in a globally distributed environment
AI Governance & MLOps: Set standards for experimentation, monitoring, CI/CD pipelines, and lifecycle management of LLM and ML models