Qingzi Jiang is a Data Scientist specialising in Applied Machine Learning and Generative AI, with a focus on building product-facing AI applications, agentic systems, and robust evaluation frameworks. Her work spans LLM application development, agent and multi-agent system design, and the eval pipelines needed to make AI systems reliable, scalable, and production-ready.
She has hands-on experience training machine learning models, building recommendation engines, developing AI features, AI agents, evaluation frameworks, and eval pipelines, with a focus on building trustworthy AI systems and improving the quality, reliability, and practical impact of AI products. Her current interests centre on AI trust, evaluation, and the challenges of assessing real-world AI systems.