LLM Evaluation

James Wu

Worked at Intuit.

James Wu is a multi-agent orchestration and LLM evaluation specialist with deep expertise in designing agentic AI systems, prompt engineering, model benchmarking, and evaluation frameworks. Previously at Intuit, he honed his skills in building scalable, production-grade AI solutions that drive measurable business outcomes. His experience spans diverse verticals, including fintech, healthcare, e-commerce, and enterprise SaaS, having contributed to initiatives at companies such as Salesforce, UnitedHealth Group, and Shopify in various technical and advisory capacities. James brings a strong foundation in retrieval-augmented generation, multi-agent workflow design, LLM fine-tuning, and systematic evaluation pipelines, making him a practitioner focused on reliability, performance, and real-world deployment of AI systems.