System / Portfolio
MR / 01Ottawa, Canada

MATTHEWROCKY

  • AI Engineer
  • LLM Systems
  • Trustworthy AI

Specialties: LLM & Multimodal Systems, RAG & Agentic Systems, Trustworthy AI, AI Applications

I build scalable LLM-powered systems, from research to production.

View ProjectsGitHubLinkedInContact
Signal / NominalOpen to Work
01 / Selected Work

Systems built to answer hard questions.

Research and production systems spanning LLM evaluation, applied AI ethics, and full-stack data tooling.

03Project Modules
Module / 01
Record / Project
University of Ottawa

Hallucination Detection in LLMs

Systematization-of-Knowledge research + full-stack dashboard

System Overview

Compared 8 hallucination-detection methods across a 200-case benchmark. The top method reached 90.5% accuracy — notably, a simpler grounded approach outperformed more complex CRITIC/CoVe pipelines.

90.5%Accuracy
8Methods
200Cases
Technology / Stack
  • 01FastAPI
  • 02Next.js
  • 03React
  • 04Local Vector Retrieval
Live DemoSourcePaper
Inspect system
Module / 02
Record / Project

Autonomous Taxi AI Ethics

Uncertainty-aware navigation prototype

System Overview

Flags risky drop-off zones instead of treating missing information as safe, weighing incident reports, severity, and recency against map-based risk zones.

Technology / Stack
  • 01React
  • 02Vite
  • 03TypeScript
  • 04Map Risk Overlays
Live DemoSource
Inspect system
Module / 03
Record / Project

LoopLens

2026 National AI Hackathon — Government of Alberta / AGI Ventures Canada

System Overview

Detects circular public-funding patterns through an interactive dashboard, network graphs, chatbot-driven analysis, and automatic memo generation.

Technology / Stack
  • 01Python
  • 02FastAPI
  • 03Pandas
  • 04Polars
  • 05DuckDB
  • 06React
  • 07Next.js
  • 08Recharts
  • 09React Flow
Live DemoSource
Inspect system
02 / About

Engineering judgment, from research to production.

Operator Profile / MRExpected / 2027
5+Years / Software Engineering
2027M.Eng / In Progress

Systems Science & Engineering (Interdisciplinary AI), University of Ottawa

I've spent the last five-plus years as a software engineer, and the last stretch of that immersed in AI/ML — building systems that need to hold up in production, not just in a notebook.

These days that means LLM pipelines, retrieval-augmented generation, and the unglamorous plumbing that makes a model actually trustworthy at scale. I'm currently pursuing an M.Eng in Systems Science & Engineering (Interdisciplinary AI) at the University of Ottawa to sharpen the research side of that work.

Experience01
5+ years in software engineering
Location02
Ottawa, Canada
Focus03
Production LLM systems, RAG, and trustworthy AI
Education04
University of Ottawa
03 / Toolkit

A working specification for production AI.

Languages, frameworks, data systems, and infrastructure used across the portfolio's research and production work.

DocumentMR-2001
Revision5.0
MR

Toolkit / Datasheet

AI systems engineering specification

Part No.
MR-2001
Revision
5.0
Groups
05
Row / 01

AI / ML

  • 01LLM APIs (OpenAI · Claude · Gemini)
  • 02LangChain
  • 03RAG
  • 04AI Agents
  • 05Hallucination Detection
  • 06PyTorch
Row / 02

DATA

  • 01Pandas
  • 02Polars
  • 03DuckDB
  • 04SQL
  • 05NLP
Row / 03

BACKEND

  • 01Python
  • 02FastAPI
  • 03Flask
  • 04REST APIs
Row / 04

FRONTEND

  • 01React
  • 02Next.js
  • 03TypeScript
  • 04Tailwind CSS
Row / 05

INFRA

  • 01AWS
  • 02Docker
  • 03CI/CD
Specification / Technology InventoryProduction / Research
04 / Contact
Channel / Direct

LET'S BUILDSOMETHINGWORTH SHIPPING.

Status / Open to Work / Ottawa / Remote

Open to remote & hybrid opportunities, collaborations, and interesting problems.

Start a ConversationLinkedInGitHub