Applied AI product engineer · Montréal
I build local-first products, governed agent systems, and practical automation—then test the claims they make.
Position / 01
I came to software through operations, marketing, and direct client problems. That route taught me to translate ambiguous human needs into bounded workflows, useful interfaces, and evidence that a system actually works.
Private pre-release product
A clean, local-first macOS voice workspace for dictation, meetings, evidence-grounded notes, and structured memory.
Deterministic vocabulary correction reduced delivered-text WER from 4.74% to 4.09% on Echo’s retained 13-fixture generated regression suite.
Private business project
A model- and runtime-independent reference for permissions, mission contracts, artifact validation, and evidence-backed AI workflows.
The reference workflow blocks undeclared permissions and cannot pass until its required evidence and report artifacts satisfy explicit validators.
Open source
A brief-driven Python engine that plans, selects, and packages short-form ad campaigns into reviewable production artifacts.
One validated brief produces six concepts and three stable ad specifications plus posting copy, QA, and a manifest; production ranking remains private.
Practice / 02
Communication / 03
English. Français. Español.
Technical work is clearer when the people around it feel understood.