Portfolio // 2026

Engineering intelligent SYSTEMS at scale

I'm Peter Yousefi, a software developer specializing in AI operations, prompt architecture, and cloud computing — designing and evaluating robust LLM solutions for real technical problems.

Input
Real problems
Process
RAG + evaluation
Infra
Cloud & APIs
Output
Shipped systems
Scroll
Portrait of Peter Yousefi
Toronto, ON2026
About // Who I Am

I design and evaluate robust LLM solutions to solve real-world technical problems.

I work across the AI stack — retrieval-augmented generation, prompt architecture, and automated evaluation — paired with the cloud infrastructure that gets it into production. Recently that's meant building tools like an AI campaign generator for small businesses and a civic-notification system that collapses hours of manual coordination into under two minutes.

Before AI operations, I spent time in logistics coordination and society leadership — which is probably why I care as much about the person who has to use the system as I do about the model behind it.

EducationB.Sc. Computer Science, Trent University
Class2026
LocationToronto, ON
StatusOpen to opportunities
FocusAI Ops · RAG · Cloud Infra
What I Build With
4 groups / 12 capabilities

The Stack

A toolkit shaped by shipping AI systems end-to-end — from model behavior to the infrastructure it runs on.

01

AI & Machine Learning

Prompt EngineeringLLM EvaluationRAG Pipeline DevelopmentAPI Integration & OCR
02

Cloud & Infrastructure

AWSDatabricksCloud Computing
03

Core Development

PythonSQLGit / GitHub
04

Professional

Cross-Functional CollaborationStakeholder CommunicationProcess ImprovementTeam Leadership & Mentorship
Selected Work

Projects

Systems built to be evaluated, deployed, and trusted — not just demoed once.

Lumina — AI marketing campaign generator logo
01 / 02

Lumina

Small business owners were losing hours per campaign writing copy, sourcing images, and tying promotions to local events — Lumina turns a business description into a full ready-to-publish campaign in minutes. It directs IBM watsonx (Granite) through a five-step workflow to research nearby events and generate on-brand captions, email copy, and imagery, with every field owner-editable before anything goes live — and a full offline fallback mode so it runs with zero API keys.

FlaskIBM watsonx (Granite)Prompt ArchitectureOffline Fallback Mode
View on GitHub →
GeoShield — prescribed burn jurisdiction and civic notification tool
02 / 02

GeoShield (WildfireGIS)

Land managers were spending 2–4 hours per prescribed burn identifying which municipality a burn boundary touched, tracking down the mayor and fire chief's contact details, and drafting a notification — GeoShield automates the entire chain down to under 90 seconds. It directs an AI model to draft calm, professional civic notifications, with unverified contacts flagged so a human always reviews before sending.

.NET 8.0IBM watsonx.aiLlama 3.3 70B InstructGIS
View on GitHub → Built at the IBM AI Builders Challenge
Experience

Track Record

Where the work happened, and what came out of it.

Jul 2024 — Present

Avalogistics

Logistics Coordinator · Toronto, ON
  • Booked and managed international ocean, air, and ground freight shipments; renegotiated 3PL carrier contracts, cutting overall freight costs by roughly 12% without sacrificing transit times.
  • Built a tracking routine to flag at-risk shipments earlier, giving sales and purchasing teams lead time to notify customers proactively.
  • Tightened up commercial invoice and customs paperwork review, reducing avoidable hold-ups at the border.
Sep 2025 — Dec 2025

Trent University

Grader · Oshawa, ON
  • Left detailed comments on every assignment pointing to the exact concept or resource behind each mistake, rather than just marking it wrong.
  • Ran one-on-one debugging sessions focused on teaching students to isolate a bug themselves instead of handing over the fix.
Sep 2021 — Dec 2022

SCS & ECA Concordia

VP of Social / Social Director · Montreal, QC
  • Rebuilt the event calendar around direct member feedback and delegated ownership across an 8-person committee — flagship events grew participation by 40%, and the society won "Event of the Year" twice across 12 competing societies.
  • Acted as the on-the-ground point of contact for 200+ attendees and a rotating volunteer team, resolving problems in real time.
Resume

Dossier

File
PDF · 1 page
Degree
B.Sc. CS
Class
2026
Status
Open to opportunities
Download
resume.pdf Open in new tab →
Let's Build Something

Get in touch.

Open to opportunities in AI operations, LLM engineering, and cloud infrastructure. If you've got a hard problem worth another set of hands on, I'll answer.

pete@petery.org Click to copy