Software Engineer (Python, SQL)

About The Company

Optum Insight is a leading healthcare technology organization dedicated to transforming the healthcare ecosystem through innovative data and information flow solutions. Our mission is to create a more connected and efficient healthcare system by removing friction and fostering alignment among care providers, payers, and consumers. With deep industry expertise and cutting-edge technology, we empower organizations to reduce costs, improve risk management, enhance quality, and drive revenue growth. Our commitment to delivering results that positively impact lives is at the core of everything we do. We foster a dynamic environment that encourages continuous learning, growth, and collaboration, enabling our team members to make meaningful contributions to healthcare transformation.

About The Role

We are seeking a highly skilled Lead Software Engineer - Remote to join our team. In this role, you will be responsible for designing, building, and scaling advanced agentic AI systems and machine learning solutions aimed at improving healthcare delivery and operational efficiency. You will architect end-to-end question answering systems, develop multi-agent workflows, and integrate these solutions with our internal AI platform, UAIS. Ensuring responsible and compliant AI deployment within a regulated environment such as HIPAA is a critical aspect of this role. The ideal candidate will possess extensive software engineering expertise, hands-on experience with large language models (LLMs), retrieval augmented generation (RAG), agent/tool use, and familiarity with cloud and data platforms. This position offers the flexibility to work remotely from anywhere within the U.S., with some in-office requirements for candidates in Minneapolis or Washington, D.C.

Qualifications

• Bachelor's degree in Engineering, Computer Science, IT, or a related field
• 12+ years of total IT experience
• 8+ years of hands-on software development, data engineering, or analytics with a focus on AI/ML delivery (Azure preferred), using Scala, Python, or PySpark
• 4+ years of experience working with Databricks
• 4+ years of experience with ADF/Airflow for orchestration and scaling
• 4+ years of experience with big data technologies and streaming platforms such as Hadoop, MapReduce/HDFS, Spark, Kafka; Docker/Kubernetes
• 4+ years of experience with MySQL and NoSQL databases
• 4+ years of experience working within Agile/Scrum methodologies, GitHub, Jenkins CI/CD, and JUnit, with a strong focus on coding standards and code reviews
• 2+ years of experience with LLMs and Generative AI tools, including Langchain, LangGraph, RAG, Vector DB, Azure Open AI, MCP Server, and LangFuse
• 2+ years of experience with container technologies like Docker and Kubernetes
• 1+ years of experience building full-stack or service-oriented applications using frameworks such as FastAPI/Flask, Node.js, React/Angular, TypeScript, HTML/CSS

Responsibilities

• Design and implement multi-agent workflows where large language models (LLMs) plan, decompose tasks, invoke tools and APIs, and synthesize answers from diverse data sources and services
• Develop retrieval augmented generation (RAG) and hybrid search pipelines to facilitate robust question answering over clinical and operational data
• Code, test, document, and maintain high-quality, scalable Big Data and cloud-based solutions
• Create scalable microservices and APIs to integrate agent capabilities into clinician tools and internal applications
• Develop prototypes and proof-of-concept solutions, conduct design and code reviews to ensure delivery quality and mitigate risks
• Leverage and adapt LLMs through prompt engineering, grounding, domain adaptation, and guardrails to meet healthcare-specific requirements
• Establish evaluation frameworks to measure model faithfulness, helpfulness, bias, toxicity, privacy leakage, and overall quality, incorporating automatic and human-in-the-loop assessments
• Collaborate with data engineering teams to build feature stores, retrieval pipelines, embeddings, and ETL/ELT processes on platforms like Spark and Databricks
• Define and develop APIs for enterprise-wide data integration, optimizing data access for low latency inference
• Own MLOps/LLMOps processes, including CI/CD pipelines, automated testing, model versioning, lineage, and deployment strategies such as blue/green or canary releases
• Instrument Service Level Objectives (SLOs), Service Level Indicators (SLIs), and cost KPIs with dashboards and alerts to monitor system performance and efficiency
• Lead production deployments on internal platforms, ensuring observability, reliability, and cost control measures are in place
• Champion security, privacy, and compliance standards aligned with HIPAA and other regulated industry controls, including access controls, encryption, and auditability
• Collaborate with legal, compliance, and clinical safety teams to operationalize responsible AI principles
• Analyze customer requirements, define technical architecture, and contribute to product delivery roadmaps
• Provide effort estimates, resource planning, and technical documentation; mentor engineers and data scientists; stay current with industry trends and advancements

Benefits

• Comprehensive health benefits package
• Incentive and recognition programs
• Equity stock purchase options
• 401(k) retirement plan contributions
• Flexible remote work environment
• Opportunities for professional development and career growth
• Supportive and inclusive workplace culture

Equal opportunity

We are proud to be an Equal Employment Opportunity employer. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, or any other basis protected by federal, state, or local law.