About me
Banking product strategy meets hands-on AI engineering.
I'm a Product Manager at TD Bank with over a decade of experience across Canada's banking landscape — from the challenger energy of EQ Bank to the scale of one of the Big 5. I've owned deposit strategy, digital banking experiences, and the P&L that comes with them.
But here's what makes me different: I don't just define AI product strategy — I build with it. I design and ship real AI-powered tools using LLMs, agents, MCP servers, and RAG pipelines. No hand-waving. No "AI-powered" buzzwords on a slide. Working software.
I sit at an unusual intersection: I understand financial services regulation, deposit products, and what it takes to move a billion-dollar portfolio — and I can architect an end-to-end AI pipeline over a weekend. That combination is rare, and it's what I bring to every team I work with.
10+
years in Canadian banking
2 banks, 1 builder
EQ Bank → TD Bank, always at the intersection
Big 5 × Challenger
P&L ownership, deposit strategy, digital banking
Credentials
Expertise
What I Bring
Banking & Product
PRODUCT LEADERSHIP
End-to-end ownership of digital banking products from strategy through delivery and iteration
BANKING DOMAIN
Deep expertise across deposit products, digital channels, and the Canadian banking ecosystem
REGULATORY & COMPLIANCE
Navigating OSFI, FCAC, and Canadian financial regulatory frameworks with confidence
AI & Builder Stack
AGENT ARCHITECTURE
Harness design, tool-use loops, reflection cycles, multi-agent orchestration and swarm topologies
RAG & RETRIEVAL SYSTEMS
End-to-end pipeline design — ingestion, chunking, embedding, hybrid search, reranking, generation
LOCAL LLM DEPLOYMENT
Model quantization, inference optimization, hardware-aware serving and benchmarking
CONTEXT & MEMORY
Context window management, token budget design, agent memory architectures (episodic, semantic, external)
MCP ARCHITECTURE
Custom MCP server design and production deployment, multi-server orchestration, tool/resource exposure
VOICE & MULTIMODAL PIPELINES
STT→LLM→TTS stack design, real-time streaming, latency optimization for voice AI systems
Projects
Things I've Built
Banking on AI
A weekly newsletter at the intersection of AI and Canadian digital banking — published on Beehiiv, read by banking professionals and AI builders.
The entire pipeline is automated: Gmail → Claude API → Beehiiv publishing, powered by MCP servers and Inngest background jobs. Zero manual publishing steps.
RAG-Based AI Voice Agent
A voice-enabled AI assistant built on Retrieval-Augmented Generation — demonstrating end-to-end AI systems thinking, not just prompting.
This wasn't about writing better prompts. It was about architecting a full pipeline: ingestion, embedding, retrieval, generation, and voice output — all working together.
© 2026 Kiran Khutal. Built with Next.js & Tailwind CSS.