At Quantiphi Analytics, I led an LLM migration that cut inference costs by about 70% while maintaining production-grade output, saving the client about $30k annually. I also owned sprint planning, backlog, and dependency tracking across three concurrent GenAI initiatives.
Earlier at Quantiphi Analytics, I owned delivery of an Intelligent Document Processing platform from PoC through production. I also delivered an insurance claims workflow that reduced intake time by 60% and a public-sector document pipeline that processed 5,000+ reports annually with 95%+ extraction accuracy.
