Lead AI Engineer - Remote

UnitedHealth Group•Eden Prairie, MN

7d•$145,500 - $249,500•Remote

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. We are looking for a Senior GenAI Developer with solid hands-on expertise in both open source and AWS Generative AI stacks. You will design and build production-ready RAG pipelines, agentic AI workflows, and knowledge base chatbots. You will work closely with architects and business stakeholders to deliver accurate, low-hallucination, observable AI solutions at enterprise scale. 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.

Requirements

Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field
8+ years of overall software / AI engineering experience
2+ years of direct hands-on experience building and deploying GenAI / LLM-based applications in production
Solid Python development skills - primary language for AI engineering work
Demonstrated portfolio or project experience with RAG pipelines, vector databases, and agentic architectures
Driver’s License and access to reliable transportation

Nice To Haves

AWS Certified AI Practitioner (AIF-C01) or Generative AI Developer (AIP-C01) certification
AWS Certified Cloud Practitioner or Developer Associate
AI/ML Specialty
Experience with Graph RAG for complex entity-relationship knowledge bases
Experience with Semantic Kernel as an alternative orchestration framework
Knowledge of Human-in-the-Loop systems - expert review/voting UI for AI answer correction
Familiarity with fine-tuning open-source LLMs (LoRA / QLoRA) on domain-specific datasets
Exposure to Amazon Connect integration with Bedrock Agents via Lex V2 for contact centre AI

Responsibilities

Design and build production-grade RAG pipelines using LangChain and LangGraph for stateful agentic workflows
Develop and maintain knowledge base chatbots with semantic search, source attribution, and multi-turn conversation memory
Implement advanced retrieval strategies - Hybrid Search (vector + keyword), HyDE, and Hierarchical / Small-to-Big chunking
Build and manage multi-agent orchestration architectures with Agentic RAG patterns (Corrective RAG, Self-RAG)
Integrate LLMs (Claude, GPT-4o, Llama 3, Mistral) via API and open-source hosting (Fireworks AI, Groq)
Design and operate vector databases - Pinecone, Weaviate, or PGVector - for semantic knowledge storage
Build AWS Bedrock-based solutions using Bedrock Agents, Knowledge Bases, and Guardrails
Set up evaluation frameworks using Ragas (faithfulness, relevance scoring) and maintain Golden Datasets for CI/AI testing
Implement LLM observability using LangSmith or Phoenix - trace calls, debug hallucinations, monitor costs
Apply PII redaction pipelines on ingested documents and enforce data security using Model Context Protocol (MCP)
Deploy AI backends using FastAPI and Docker with OpenTelemetry for system-wide monitoring
Collaborate with Solution Architects to produce HLDs, LLDs, and developer-facing documentation for AI components