I make AI systems observable, evaluated, and ready for production.
AI Observability Architect at PepsiCo with 14+ years in enterprise engineering. I help teams turn fragile LLM demos into RAG and AI systems that stay reliable, measurable, and cost-efficient in production.
"Drove Wipro's HOLMES Cognitive Search from inception through production rollouts — handling customer deliveries single-handedly and improving its accuracy."
What’s the difference between prompt engineering, context engineering, harness engineering, loop engineering, and evaluation engineering? A side-by-side comparison with diagrams for AI engineers building production systems.
On rivers, cells, chemistry teachers, and the illusion of a permanent self: a non-technical exploration of identity, impermanence, and the observer within.