Sr AI/ML Engineer

UnitedHealth Group•Eden Prairie, MN

2d•$120,100 - $214,500•Remote

About The Position

As a Senior AI/ML Engineer at Optum, you will build and deploy production-grade large language model (LLM) agents and Retrieval-Augmented Generation (RAG) pipelines to automate the detection, triage, and remediation of platform and application issues. The role combines machine learning engineering, system observability, and developer experience, with responsibility for designing orchestration, guardrails, and evaluation frameworks for high-impact AI capabilities. You will work closely with SRE, InfoSec, and platform teams to create scalable, secure, and responsible AI solutions integrated into software development workflows. The position offers telecommuting from anywhere within the U.S., subject to UnitedHealth Group’s Telecommuter Policy.

Requirements

At least 4 years of software engineering or machine learning engineering experience.
At least 4 years of experience with Python, including working knowledge of agent frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
At least 2 years of hands-on experience building with LLMs, including prompt engineering, tool or function calling, and agent or multi-step orchestration.
At least 2 years of experience designing and shipping production RAG systems, including embeddings, vector databases, and retrieval evaluation.
At least 2 years of experience integrating third-party APIs and building production backend services.
At least 2 years of experience with cloud platforms (Azure, AWS, or GCP), containers, and CI/CD pipelines.
At least 2 years of experience building LLM evaluation and testing workflows rather than relying on manual spot checks.
Candidates must pass a drug test before beginning employment.

Nice To Haves

Bachelor’s degree or equivalent experience, such as 4 or more years of software engineering or machine learning engineering experience in lieu of a degree.
Experience with model fine-tuning or parameter-efficient fine-tuning (PEFT) techniques.
Experience integrating agents with enterprise observability and security platforms via APIs and MCP-style tool interfaces.
Proven ability to work across multidisciplinary teams, such as SRE, InfoSec, and platform engineering, and translate operational pain points into technical requirements.

Responsibilities

Design, develop, and deploy AI-powered solutions for complex business challenges, emphasizing responsible use of AI.
Build production LLM agents that automate detection, triage, and remediation of platform and application issues.
Design and tune RAG pipelines over runbooks, incident history, logs, code, and internal documentation, including chunking, embeddings, vector stores, search, and reranking.
Implement agent orchestration, including tool and function calling, multi-step planning, multi-agent handoffs, memory, and state management.
Build supporting agent infrastructure and software, including tool wrappers, guardrails, human-in-the-loop approval paths, and fallback behavior.
Own model and prompt engineering, including model selection, prompt and context optimization, output structuring, cost and latency tuning, and fine-tuning or parameter-efficient techniques where warranted.
Build evaluation pipelines, define quality metrics for agent and RAG behavior, and iterate based on evaluation results.
Integrate agents with observability and security platforms through APIs and Model Context Protocol (MCP) tool interfaces to deliver capabilities inside developer workflows.
Evaluate emerging AI trends and contribute reusable patterns, components, and documentation across the enterprise AI development lifecycle.
Use enterprise-approved AI tools to streamline workflows, automate tasks, and drive continuous improvement.