UnitedHealth Group is hiring a Lead AI/ML Engineer to architect and drive the technical vision for AI systems that improve health outcomes and operational efficiency. You'll lead the design of multi-agent platforms and mentor engineers across a globally distributed team.
What You'll Do
- Lead AI System Design: Architect and evolve 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.
What We're Looking For
- 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 Have
- 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.
Technical Stack
- Python, PyTorch, Hugging Face, scikit-learn, Spring Boot
- Azure OpenAI, Azure Functions, Azure Event Hubs, Azure Cognitive Search, Azure Cosmos DB
- LangChain, AutoGen, Semantic Kernel
Team & Environment
You'll be part of a globally distributed engineering team.
Benefits & Compensation
- Compensation range: $112,700 to $193,200 annually
- Comprehensive benefits package
- Incentive and recognition programs
- Equity stock purchase
- 401k contribution
Work Mode
This is a hybrid position open to candidates in the United States.
Our culture is guided by inclusion, talented peers, comprehensive benefits, and career development opportunities. We are on a mission to help people live healthier lives and make the health system work better for everyone.
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.
