Lawrence Livermore National Laboratory
Software Engineer - AI RAG & Data Virtualization
Lawrence Livermore National Laboratory, Livermore, California, United States, 94551
Software Engineer - AI RAG & Data Virtualization
Join us and make YOUR mark on the World! Are you interested in joining some of the brightest talent in the world to strengthen the United States' security? Come join Lawrence Livermore National Laboratory (LLNL) where our employees apply their expertise to create solutions for BIG ideas that make our world a better place. We are dedicated to fostering a culture that values individuals, talents, partnerships, ideas, experiences, and different perspectives, recognizing their importance to the continued success of the Laboratory's mission. Pay Range $168,780 - $214,032 annually Job Description
We're looking for a mid-level Software Engineer to join our Enterprise Data Management team supporting AI enablement. In this role, you will help design, develop, and deploy solutions that integrate Retrieval-Augmented Generation (RAG) pipelines and data virtualization technologies to empower AI-driven decision-making across critical business functions including Finance, HR, Procurement, Environmental, Safety & Health, and Facilities and Infrastructure. You will work closely with application developers, data scientists, product owners, and business analysts to ensure that high-quality, context-rich data is accessible and usable by AI applicationshelping to unlock business insights and operational efficiency. This position offers a hybrid schedule, blending in-person and virtual presence. You will have the flexibility to work from home one or more days per week. You will Build and maintain Retrieval-Augmented Generation pipelines, integrating LLMs (e.g., OpenAI, Anthropic, etc.) with enterprise document stores and vector databases. Develop scalable, secure APIs and microservices that enable RAG-based applications (e.g., AI copilots, intelligent document search). Work with application development teams to optimize retrieval performance and improve accuracy through prompt engineering and grounding techniques. Collaborate with data engineering teams to integrate virtualized data sources (e.g., via Denodo) into AI workflows. Build connectors and middleware to access and transform real-time operational data for consumption by LLMs and analytics services. Ensure solutions maintain data lineage, access controls, and governance policies. Partner with application developers and stakeholders across operational areas such as Finance, HR, and Procurement to identify AI opportunities and build tools that reduce manual workflows (e.g., invoice summarization, policy Q&A, contract analysis). Deliver intuitive UIs, dashboards, or endpoints that expose AI functionality to business users. Monitor system performance and iterate on feedback to improve usability, explainability, and relevance. Perform duties as assigned Qualifications
Ability to obtain and maintain a U.S. DOE L-level security clearance in the future. This requires U.S. Citizenship. Bachelor's degree in Computer Science, Engineering, or related technical field. Significant experience in software development, preferably in enterprise or data-rich environments. Advanced Python, JavaScript/TypeScript, or Java experience for backend and integration development. Significant experience building AI-powered applications, particularly using RAG architectures, vector databases (e.g., OpenSearch, pgvector, Pinecone), and LLM APIs (e.g., OpenAI, Azure OpenAI). Significant experience with data virtualization tools (Denodo) or similar data integration platforms. Significant experience in leveraging RESTful API development, microservices, and cloud platforms (e.g., AWS, Azure). Advanced knowledge of data privacy, security best practices, and compliance when working with operational data. Qualifications We Desire Experience working within Agile/Scrum environments supporting cross-functional development teams Knowledge of enterprise data systems (e.g., Oracle Finance, Oracle HCM Cloud, PeopleSoft, Hexagon/Infor EAM). Exposure to vector embeddings, semantic search, and knowledge graph technologies. Familiarity with DevOps, CI/CD pipelines, and containerization (e.g., Docker, Kubernetes). Advanced knowledge of prompt tuning, feedback loops, and human-in-the-loop AI design.
Join us and make YOUR mark on the World! Are you interested in joining some of the brightest talent in the world to strengthen the United States' security? Come join Lawrence Livermore National Laboratory (LLNL) where our employees apply their expertise to create solutions for BIG ideas that make our world a better place. We are dedicated to fostering a culture that values individuals, talents, partnerships, ideas, experiences, and different perspectives, recognizing their importance to the continued success of the Laboratory's mission. Pay Range $168,780 - $214,032 annually Job Description
We're looking for a mid-level Software Engineer to join our Enterprise Data Management team supporting AI enablement. In this role, you will help design, develop, and deploy solutions that integrate Retrieval-Augmented Generation (RAG) pipelines and data virtualization technologies to empower AI-driven decision-making across critical business functions including Finance, HR, Procurement, Environmental, Safety & Health, and Facilities and Infrastructure. You will work closely with application developers, data scientists, product owners, and business analysts to ensure that high-quality, context-rich data is accessible and usable by AI applicationshelping to unlock business insights and operational efficiency. This position offers a hybrid schedule, blending in-person and virtual presence. You will have the flexibility to work from home one or more days per week. You will Build and maintain Retrieval-Augmented Generation pipelines, integrating LLMs (e.g., OpenAI, Anthropic, etc.) with enterprise document stores and vector databases. Develop scalable, secure APIs and microservices that enable RAG-based applications (e.g., AI copilots, intelligent document search). Work with application development teams to optimize retrieval performance and improve accuracy through prompt engineering and grounding techniques. Collaborate with data engineering teams to integrate virtualized data sources (e.g., via Denodo) into AI workflows. Build connectors and middleware to access and transform real-time operational data for consumption by LLMs and analytics services. Ensure solutions maintain data lineage, access controls, and governance policies. Partner with application developers and stakeholders across operational areas such as Finance, HR, and Procurement to identify AI opportunities and build tools that reduce manual workflows (e.g., invoice summarization, policy Q&A, contract analysis). Deliver intuitive UIs, dashboards, or endpoints that expose AI functionality to business users. Monitor system performance and iterate on feedback to improve usability, explainability, and relevance. Perform duties as assigned Qualifications
Ability to obtain and maintain a U.S. DOE L-level security clearance in the future. This requires U.S. Citizenship. Bachelor's degree in Computer Science, Engineering, or related technical field. Significant experience in software development, preferably in enterprise or data-rich environments. Advanced Python, JavaScript/TypeScript, or Java experience for backend and integration development. Significant experience building AI-powered applications, particularly using RAG architectures, vector databases (e.g., OpenSearch, pgvector, Pinecone), and LLM APIs (e.g., OpenAI, Azure OpenAI). Significant experience with data virtualization tools (Denodo) or similar data integration platforms. Significant experience in leveraging RESTful API development, microservices, and cloud platforms (e.g., AWS, Azure). Advanced knowledge of data privacy, security best practices, and compliance when working with operational data. Qualifications We Desire Experience working within Agile/Scrum environments supporting cross-functional development teams Knowledge of enterprise data systems (e.g., Oracle Finance, Oracle HCM Cloud, PeopleSoft, Hexagon/Infor EAM). Exposure to vector embeddings, semantic search, and knowledge graph technologies. Familiarity with DevOps, CI/CD pipelines, and containerization (e.g., Docker, Kubernetes). Advanced knowledge of prompt tuning, feedback loops, and human-in-the-loop AI design.