# Jueying Li > Applied AI / GenAI Engineer | LLM Systems | RAG & Multi-Agent Architectures | Python | Cloud Location: New York, New York, United States Profile: https://flows.cv/jueying I build production AI systems that combine large language models, retrieval, internal tools, and backend services to support real-world enterprise workflows. My work focuses on document understanding, context-aware conversational systems, knowledge access, and reliable end-to-end AI applications. I am especially interested in applied AI and LLM systems engineering: designing agentic workflows, integrating models with tools and structured data, and improving system performance in production. I have experience working with frameworks such as LangGraph and Google ADK, and I care deeply about choosing the right abstractions to enable rapid iteration, reliability, and scalability. A key focus of my work is performance-aware AI engineering, with strong attention to latency, token efficiency, reliability, and operational quality. I enjoy turning complex AI capabilities into practical systems that are fast, efficient, and usable in real-world environments. My background spans software engineering, full-stack development, data science, and applied machine learning, allowing me to work across the stack—from backend systems and application logic to evaluation and production deployment. I’m most excited by roles at the intersection of AI agents, LLM systems, enterprise integration, and customer-facing AI products. ## Work Experience ### Artificial Intelligence Engineer @ Danta Technologies Jan 2025 – Present | New York, United States • Designed and built production LLM systems for a Fortune 500 telecommunications client, supporting document understanding and context-aware, multi-turn conversational workflows. • Built AI architectures combining language models, retrieval, internal tools, and structured data services, leveraging frameworks such as LangGraph and Google ADK for agent orchestration and workflow design. • Transitioned from LangGraph to Google ADK to improve development velocity and simplify workflow iteration in production environments. • Drove performance optimization across AI systems with strong attention to latency, token efficiency, reliability, and operational quality. ### Data Science Intern (ML Track) @ The Janssen Pharmaceutical Companies of Johnson & Johnson Jan 2023 – Jan 2023 | Titusville, NJ • Developed AI-assisted decision-support workflows to enhance pharmaceutical sales strategies. • Explored new data sources and engineered features for an explainable ML pipeline using SHAP. • Conducted experiments on recommendation strategies to optimize lead insights for sales teams. • Analyzed territory-level sales data to generate actionable business insights for targeting decisions. ### Full Stack Developer @ Johnson & Johnson Jan 2022 – Jan 2023 | Raritan, NJ • Developed and maintained internal full-stack applications to enhance enterprise workflows. • Collaborated with stakeholders to deliver reliable tools for internal users, focusing on user needs. • Worked in an Agile/Scrum environment to ensure iterative delivery and continuous improvement. ### Software Developer @ Kunvet Jan 2018 – Jan 2019 | Irvine, CA • Contributed to the development of customer-facing web applications at Kunvet, a dynamic startup in Irvine, California. • Built and maintained frontend features using JavaScript and modern frameworks to enhance user experience. • Supported A/B testing and experimentation to inform product decisions and optimize interaction flows. ## Education ### Master of Science - MS in Computer and Information Sciences, General Cornell Tech ### Master of Science - MS in Computer and Information Sciences, General Cornell University ### Bachelor of Arts - BA in Psychology UC Irvine ### Bachelor of Science - BS in Computer Science UC Irvine ## Contact & Social - LinkedIn: https://linkedin.com/in/jueying-li-helloworld --- Source: https://flows.cv/jueying JSON Resume: https://flows.cv/jueying/resume.json Last updated: 2026-04-19