Yogendra Miraje

Yogendra Miraje is a Principal AI Engineer at FactSet who builds and deploys LLM agents in enterprise financial services. His public writing and his AI Engineer World's Fair 2025 talk on planning agents emphasize practical resilience over flashy demos — 'what is the simplest thing that actually works?', understanding failure modes and scalability constraints, and knowing when automation should stop. He co-authored a FactSet/Databricks production case study reporting large latency reductions (over 70% on code generation, ~60% end-to-end via fine-tuning), making him a strong signal for practitioners focused on shipping controllable, measurable agent systems rather than prototypes.