GenAI / Applied LLM Engineer

The GenAI / Applied LLM Engineer will design, develop, and deploy AI driven solutions that enhance Fluor s engineering, project management, and enterprise operations. This role focuses on building secure, scalable GenAI applications using modern LLM frameworks, Azure AI Foundry, enterprise data sources, retrieval augmented generation (RAG), and agentic automation patterns. The engineer will collaborate closely with digital engineering, data platform, software development, and business stakeholders to deliver production grade AI capabilities aligned with EPC project workflows. Key Responsibilities Develop, test, and deploy GenAI applications leveraging LLMs, RAG pipelines, and prompt engineering to solve business challenges across Fluor s EPC value chain. Build scalable backend services and APIs in Python and C# supporting AI workloads. Implement enterprise grade AI solutions using Azure AI Foundry , Azure OpenAI, Vector Search, and secure data integrations. Design and optimize data ingestion, transformation, and retrieval layers using SQL Server, Cosmos DB, and Azure data services. Develop UI components and front end features using Angular for internal AI tools and applications. Configure and finetune opensource LLMs (where permitted) or apply parameter efficient tuning techniques for enterprise tasks. Integrate AI models into existing digital products, workflows, and engineering automation systems. Collaborate with data engineers, architects, full stack developers, and domain SMEs to translate business needs into AI technical specifications. Apply MLOps and AI lifecycle best practices for deployment, monitoring, versioning, performance optimization, and responsible AI compliance. Ensure all solutions follow Fluor s standards for cybersecurity, quality, data privacy, and scalable architecture. Provide documentation, training, and support to help teams adopt AI capabilities. Basic Job Requirements 5+ years of professional experience in software engineering or applied AI roles. At least 3 years hands-on with LLMs, GenAI systems, or modern AI frameworks. Strong expertise in Python (core libraries, FastAPI, vector databases, data processing). Experience with Azure Cognitive Search, semantic search, and index enrichment pipelines. Knowledge of Responsible AI practices, model governance, and prompt safety evaluation. Experience with agent frameworks (Semantic Kernel, AutoGen, CrewAI). Familiarity with enterprise observability stacks (App Insights, Prometheus, OpenTelemetry) for LLM performance monitoring. Proficiency in C#/.NET and building enterprise-grade backend services. Hands-on experience with LLMs, prompt engineering, and GenAI solution development. Experience working with enterprise knowledge indexing, metadata extraction, and content enrichment. Experience with AI Foundry / Azure AI Studio, Azure OpenAI, and cloud-native AI pipelines. Solid understanding of SQL Server, Cosmos DB, and distributed data storage concepts. Strong front-end development experience with Angular. Ability to design secure, scalable, production-ready AI systems. Bachelor s or Master s degree in Computer Science, Information Technology, Data Science, or related engineering discipline. Azure certifications (AI Engineer Associate, Developer Associate) preferred. Other Job Requirements Preferred Qualifications Experience with RAG, embeddings, vector search, LangChain/LlamaIndex, or similar frameworks. Knowledge of Azure Data Factory, Azure Functions, Event Hub, or broader cloud ecosystem. Familiarity with DevOps/MLOps (GitHub Actions, Azure DevOps, model registry, CI/CD). Experience working in an EPC, industrial, or engineering-heavy enterprise environment. Exposure to agentic systems and multi-model orchestration.