Product leader building
production AI systems.
10+ years leading enterprise API, data, and platform products for Bell Canada, Rogers, and BP — now pairing that delivery discipline with hands-on LLM engineering: multi-agent orchestration, RAG pipelines, and cloud-native deployment. This page covers both the product track record and the systems I've personally built and shipped.
- Owned the product lifecycle for Bell's enterprise API platform across customer, billing, and product-catalog domains, supporting 5 downstream business units
- Increased enterprise API adoption by 40% through standardized API contracts and developer self-service improvements
- Improved data accuracy by 30% and cut order-processing latency by 20% by redesigning orchestration workflows and embedding governance automation into CI/CD
- Led PI Planning and cross-functional agile ceremonies across multiple squads
- Led roadmap planning for an on-prem to Azure cloud migration, enabling 2× faster analytics delivery and cutting infrastructure costs by 40%
- Designed and prioritized API-enabled digital services supporting new business models
- Reduced operational downtime risk by 25% through predictive risk modeling
- Defined MVP scope, user stories, and business-value metrics for operational digitization initiatives with global stakeholders
- Standardized requirements documentation, reducing rework by ~25%
- Directed multi-departmental R&D and IT project delivery, maintaining a 95% on-time completion rate
- Improved project turnaround time by ~20% through process optimization and data-driven reporting
- Developed Python and MATLAB machine-learning pipelines for cognitive neuroscience research
- Statistical analysis work published in Biological Cybernetics
Applied AI systems designed, built, and deployed end to end — spanning healthcare documentation, multi-agent planning, legal-tech retrieval, and cloud infrastructure.
MediScribe — AI Clinical Documentation Assistant
Turns typed or dictated consultation notes into structured medical summaries, action items, and patient-ready letters — in 19 languages.
Clinicians lose real time after every visit writing up notes, follow-ups, and patient communication — often duplicated across languages for non-native speakers. MediScribe takes typed or voice-dictated notes and generates a clinical summary, a clear action-item list, and a patient-facing email, with one-click translation into 19 languages.
Fin-Ops Travel Planner — Multi-Agent Trip Budgeting Assistant
A CrewAI crew — Flight + Forex Specialist, Travel Budget Profiler, and a Fin-Ops Travel Planner — coordinates over MCP tools to produce a day-by-day itinerary and full budget breakdown that stays within a set total.
Planning international travel usually means juggling separate tabs for flight prices, currency conversion, and daily budget guesswork with no single view of whether the trip is actually affordable. This crew runs sequentially: a Flight + Forex Specialist pulls cost context through MCP tools, a Travel Budget Profiler allocates a daily spending plan, and a Fin-Ops Travel Planner agent assembles both into a day-by-day itinerary with a final budget table — for example, a 7-day Paris trip on a $4,000 total budget, broken down to accommodation, food, transport, and entertainment per day.
Litigation Prep Assistant — Multi-Step RAG Pipeline
A production-style monorepo that extracts case facts, retrieves grounding statutes, drafts strategy documents, and reviews its own output end to end.
Litigation prep involves extracting relevant facts from case materials, grounding arguments in the right statutes, and drafting strategy documents — usually a slow, manual research process. This system runs a multi-step LLM pipeline (extraction → RAG-grounded strategy generation → drafting → automated quality review) behind an authenticated web app, structured as a real product rather than a notebook demo.
Digital Twin — Conversational AI About Me
An AI twin recruiters can talk to directly about my background, skills, and projects — grounded in my actual experience rather than generic chat.
Recruiters and hiring managers often just want a quick answer, not a full conversation. This project is a conversational digital twin, grounded in my actual experience, that can answer questions about my background and projects directly.
A newer version — serverless on AWS, built with Terraform and GitHub Actions — is deployed and being finalized; link coming soon.
I'm a product leader with 10+ years delivering enterprise API, data, and digital-transformation initiatives across telecom, energy, and life sciences — most recently owning Bell Canada's enterprise API platform across customer, billing, and catalog domains. Grounded in an M.Sc. in Computational Neuroscience, I've since gone hands-on with AI engineering: building agentic and RAG-based LLM applications with LangGraph, CrewAI, and MCP, and deploying them across AWS, GCP, Azure, and Vercel. I bring both sides to the table — the product and stakeholder discipline to scope and ship the right thing, and the technical depth to build it myself.
Product & Strategy
Product vision & roadmapping, OKR/KPI design, backlog prioritization, intake & investment governance, stakeholder leadership
Delivery & Agile
SAFe Agile / PI Planning, cross-functional squad leadership, API & data product management, JIRA, Confluence
AI & LLM Engineering
LangGraph, CrewAI, MCP, RAG pipelines, prompt engineering, evaluation & observability, agentic tool-calling
Cloud & Data
AWS, GCP, Azure, Vercel, Amazon Bedrock, Terraform, SQL, Tableau, Python