Full Stack Engineer

We are seeking a Senior Data Scientist / AI Full-Stack Engineer to design, build, and scale AI-powered analytics and application platforms. This is a hybrid role that blends data science with modern full-stack development (React/Next.js/Svelte + Node.js), with AI/ML — including natural language querying and RAG — woven through both the backend and the customer-facing product experience. You'll build the data pipelines and AI capabilities that power the platform, and ship the application layer end to end. Key Responsibilities

AI / NLP / RAG

Build and maintain RAG pipelines, vector search, and semantic query systems using LLMs (Claude or similar) Develop prompt engineering strategies and continuously improve AI output accuracy and relevance Integrate AI/ML capabilities into customer-facing UI to create smarter, adaptive user experiences Data Science & Engineering Develop and maintain SQL and Python logic for data processing and analysis Integrate and normalize data from multiple sources (logs, APIs, databases, surveys) Ensure data accuracy, consistency, and performance optimization Implement data quality validation and monitoring processes Full-Stack Application Development Architect, build, and scale the front-end application layer using React.js, Next.js, or Svelte Build backend services and APIs using Node.js (or FastAPI) Design and implement dynamic, user-configurable dashboards and visualizations (charting libraries such as ECharts, Recharts, D3, or BI tools) with filtering, drill-down, saved views, and export (PNG/CSV/PDF) Ensure platform is built for extensibility, performance, and long-term scalability Delivery & Collaboration Deliver iteratively using Agile/SAFe methodologies (PI planning, epics/features/stories, sprint execution) Maintain documentation: data architecture diagrams, AI workflow and prompt design docs Collaborate cross-functionally with program leadership, business stakeholders, and platform engineering; translate business needs into implemented solutions Support platform evolution and integration with enterprise tools (e.g., Databricks, Collibra) Required Qualifications 8–15 years of professional experience spanning data science and full-stack software development (exact range flexible depending on candidate strength across both sides) Expert-level proficiency in one or more modern UI frameworks: React.js, Next.js, or Svelte Strong backend experience with Node.js (or FastAPI/Python backend frameworks) Advanced SQL and strong Python for data processing and analysis Demonstrable hands-on experience with LLMs, prompt engineering, RAG, and/or vector search — not just conceptual familiarity Experience with state management, build tools (Webpack/Vite), and testing frameworks Solid understanding of both SQL and NoSQL database technologies Experience with a major cloud platform (AWS, GCP, or Azure) and CI/CD pipelines Experience working in Agile and/or SAFe environments Preferred Qualifications Experience building AI-powered natural language querying or "ask your data" style features in production A portfolio or examples of shipped AI-integrated features (chatbot, recommendation engine, NLP, computer vision, etc.) Familiarity with AI-specific libraries/frameworks (LangChain, TensorFlow.js) Exposure to Databricks and/or ETL/data pipeline frameworks Experience with SvelteKit Experience with performance monitoring/observability tools Knowledge of web security best practices Prior tech lead or architectural ownership role #J-18808-Ljbffr Ampcus