ABOUT THE COMPANYUncountable is building the next generation of AI-first R&D tools, empowering scientists at Fortune 500 companies to accelerate discovery through Generative AI. The platform transforms how research teams interact with complex experimental data, combining LLM infrastructure with intuitive, data-rich interfaces built specifically for scientists and R&D organizations.ABOUT THE ROLEAs LLM Applications Engineer at Uncountable, you'll be the architect of the company's LLM infrastructure, designing the retrieval systems, agentic workflows, and data pipelines that bridge the gap between complex experimental data and actionable AI insights. This is a hybrid role requiring deep full-stack expertise and hands-on experience deploying LLMs in production. You won't just be building interfaces — your work will directly modernize how the world's leading researchers interact with their data.KEY RESPONSIBILITIESImplement and optimize RAG (Retrieval-Augmented Generation) pipelines, vector databases, and prompt management systems, building the retrieval infrastructure that powers high-fidelity AI responsesBuild intuitive, AI-driven UI components that allow scientists to query, analyze, and visualize complex experimental datasets, creating LLM-first experiences that feel seamless, not bolted-onConnect LLM capabilities with core SQL databases and data analysis engines to ensure grounded, accurate AI responses across the platformDesign and scale agentic workflows and data pipelines that bridge experimental data with actionable AI insights at production gradeOwn API design, asynchronous processing, and performance optimization across the full stack, backend infrastructure and React frontendREQUIREMENTSMust-Have2+ years of software development experience with a focus on full-stack web applicationsProven experience with LLM orchestration frameworks, LangChain, LlamaIndex, Haystack, or equivalentProficiency in Python and JavaScript/TypeScript, ability to work across AI backend and React frontendSolid engineering fundamentals, API design, asynchronous processing, and performance optimizationNice-to-HaveB.S. in Computer Science or a related technical fieldExperience with LLM evaluation, measuring and mitigating hallucinations in scientific or technical contextsFamiliarity with SQL query optimization, specifically for queries serving as LLM prompt contextProduct mindset, passion for building LLM-first experiences that feel native to the userTOOLS & STACKBackend:Flask (Python), primary backend frameworkPostgreSQL, core databaseFrontend:React (TypeScript), UI developmentRedux, state managementSass, stylingAI / LLM:LangChain / LlamaIndex / Haystack, orchestration frameworksRAG pipelines, retrieval-augmented generationVector databases, semantic search and retrievalWhat's next? Learn more about Interviewing at UncountableLearn more about our engineering team: Check out our blog