I'm Kunal — a Senior Staff Engineer in Toronto who's spent 14 years turning "what if we could…" into production systems serving millions. I've shipped a Walmart chatbot that 4x'd engagement, crypto accounting infra processing 200K transactions in 5 minutes, and production RAG/GraphRAG pipelines with hybrid retrieval and agentic re-ranking. Right now I'm deep in AI agents, LLM orchestration, and local-LLM hardware, I maintain an open dataset of 80+ measured LLM benchmarks across Apple Silicon, NVIDIA and AMD, and write deep-dives read by 650K+ developers. Book me if you want a second senior opinion on your AI architecture, your local-vs-API inference strategy, or your career as an engineer moving into AI. Come with a concrete problem, leave with a concrete plan.