At Optimizely, I led delivery of the Experimentation Remote MCP Server, prototyping and building six production tools that let AI agents manage experiment entities. I also proposed the integration architecture adopted across the Opal platform and drove readiness, reliability, and correctness for its experimentation tooling.
I replaced Optimizely’s public-documentation RAG system with Google Vertex AI Search and redesigned its retrieval pipeline. Earlier, I owned the Statistical Significance service end to end, reducing costs by 98%; outside work, I build Askable, a cited-answer RAG engine, and Converse, a multi-agent LangGraph engine.
