Lead Software Engineer - Remote

UnitedHealth Group•Richardson, TX

1d•$112,700 - $193,200•Remote

About The Position

Optum Insight is improving the flow of health data and information to create a more connected system. We remove friction and drive alignment between care providers and payers, and ultimately consumers. Our deep expertise in the industry and innovative technology empower us to help organizations reduce costs while improving risk management, quality and revenue growth. Ready to help us deliver results that improve lives? Join us to start Caring. Connecting. Growing together. We are seeking a Lead Software Engineer to design, build, and scale next-generation agentic AI systems and advanced solutions that improve healthcare delivery and operations. In this individual contributor (IC) leadership role, you will operate as a hands-on technical expert, driving architecture, development, and deployment of complex AI-powered solutions. You will architect end-to-end question answering and multiagent workflows, integrate with our internal AI platform (e.g., UAIS), and ensure responsible, compliant use of AI in a regulated environment (HIPAA). The ideal candidate combines deep software engineering expertise with hands-on experience in LLMs, RAG, agent/tool use, and evaluation on modern cloud and data platforms. This role is ideal for someone who thrives on solving complex problems, enjoys working at the intersection of AI/ML and distributed systems, and wants to make a meaningful impact in a highly regulated, mission-driven environment. 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 degree in Engineering, Computer Science, IT, or related fields
10+ years of total technology experience
8+ years hands on software development/data engineering/analytics with solid AI/ML delivery (Azure preferred) with Scala, Python, PySpark
4+ years hands on with Databricks
4+ years with ADF/Airflow (orchestration/scaling)
4+ years with big data & streaming (Hadoop, MapReduce/HDFS, Spark, Kafka); Docker/Kubernetes
4+ years with MySQL and NoSQL databases
4+ years with Agile/Scrum, GitHub, Jenkins CI/CD, JUnit; solid coding standards and code reviews
2+ years with LLMs & GenAI (Langchain, LangGraph, RAG, Vector DB, Azure Open AI, MCP Server, Agents, LangFuse)
2+ years of experience with container (Docker/Kubernetes)
1+ years with Proficiency building services or full stack apps (e.g., FastAPI/Flask, Node.js, React/Angular, TypeScript, HTML/CSS)

Nice To Haves

Healthcare experience; familiarity with clinical datasets
Experience working in regulated industries, with knowledge of ethical AI/ML practices and compliance requirements
SOA and enterprise integration concepts
Publications/patents or notable open-source contributions
Proven excellent analysis, problem solving, and communication skills

Responsibilities

Design and implement (multi) agentic workflows where LLMs plan, decompose tasks, invoke tools/APIs, and synthesize answers across heterogeneous data sources and services
Build retrieval augmented generation (RAG) and hybrid search pipelines to power robust question answering over clinical and operational data
Design, code, test, document, and maintain high quality, scalable Big Data and cloud solutions
Develop scalable microservices and APIs for integrating agent capabilities into clinician tools and internal apps
Create prototypes/POCs and conduct design/code reviews to derisk delivery and raise engineering quality
Leverage and adapt LLMs; perform prompt engineering, grounding, guard railing, and domain adaptation for healthcare terminology and tasks
Design intelligent frameworks and finetune models for compliance, accuracy, and ethical standards
Establish evaluation frameworks (automatic + human in the loop) to measure faithfulness, helpfulness, bias, toxicity, privacy leakage, and overall quality
Partner with data engineering to build feature/retrieval stores, embeddings pipelines, and ETL/ELT jobs on Spark/Databricks; design analytics models and rules engines
Define and develop APIs for integrations across the enterprise; improve data access patterns for low latency inference
Own MLOps/LLMOps: CI/CD for models/prompts, automated tests (unit/contract/eval), versioning, lineage, rollback; enable blue/green or canary releases
Instrument SLOs/SLIs (latency, availability, hallucination/defect rate) and cost KPIs (tokens, GPU hours) with dashboards and alerts
Lead production deployments on internal platforms (e.g., UAIS) with solid observability, reliability, and cost controls
Champion HIPAA and regulated industry controls; integrate access controls, PHI/PPI safeguards, data minimization, encryption, and auditability
Collaborate with legal, compliance, and clinical safety to operationalize Responsible AI principles
Analyze and define customer requirements; assist in defining product technical architecture and delivery roadmaps
Provide effort estimates and inputs for resource planning; collaborate with QA, architecture, and peer teams
Write technical documentation, support production, and mentor engineers, and keep skills current through continuous learning