Software developer · Applied AI

Useful software.Learning systems.

I build software and explore how machine learning turns data into useful decisions.

Montréal, Canada/Polytechnique Montréal
A LOOK INSIDE THE TAXI LAB
Taxi at row 3, column 3. Passenger at R. Destination B.RGYB0 · 1 · 2 · 3 · 4
Small world. Interesting decisions.500 states. 6 actions. One destination.
CODE, DATA, AND A FEW GOOD QUESTIONS.Scroll to explore

From the problem to the details.

Explore the ideas, interactions, and engineering behind three applied AI projects.

What the results made me question.

Three editorial observations from saved educational notebook outputs. The original notebooks are not published here.

01 / Lab NotesGenomic classification

An ensemble does not automatically improve performance

Observation

On raw data, the recorded RF + SGD ensemble reached 0.8279 validation macro-F1, just below Random Forest at 0.8293.

Practical consequence

Keep a simple baseline and measure what the added method actually contributes.

Read the note
02 / Lab NotesCustom MLP and PyTorch on Fashion-MNIST

Learning rate changes the outcome

Observation

Across three recorded learning rates, both implementations changed markedly; at 0.0001 the saved test accuracies were 38.47% and 66.04%.

Practical consequence

Inspect training configuration before attributing a gap to architecture or library choice.

Read the note
03 / Lab NotesTaxi-v3 reinforcement learning

A fair comparison needs a shared evaluation protocol

Observation

Saved outputs include 39 successes in 100 Monte Carlo episodes and 200 in 200 Q-learning episodes, under differing conditions.

Practical consequence

Compare methods with shared starts, limits, episode counts, and multiple seeds.

Read the note

Software meets the real world.

Experience across banking technology and logistics.

2025

CEVA Logistics

Logistics & data

A logistics environment connecting CargoWise, SQL, operational indicators, and dashboards.

CargoWiseSQLDashboards
2024

Banque Nationale

Software development internship

A software development environment at Banque Nationale, working with a Java and Spring Boot stack alongside Python, Kafka, Jenkins, and Docker.

JavaSpring BootPythonKafkaJenkinsDocker

Detailed responsibilities and exact dates will be added with the final résumé.

Technical expertise, proven through practice.

34 skills shown

Related practices

REST API, BDD, CI/CD, Agile, and Scrum appear as working practices, without invented brand marks or proficiency scores.

REST APIBDDCI/CDAgileScrum
Logo sources

Simple Icons · Devicon · Gymnasium · OpenAI. Git logo by Jason Long (CC BY 3.0); Jenkins logo by Frontside for Jenkins (CC BY-SA 3.0); Angular logo under CC BY 4.0. The marks identify tools and do not imply endorsement.

Curious about the system.Careful about the details.

My focus is software development, with a growing interest in applied AI. I’m interested in the whole path from a problem to a working system: how data is represented, how software is organized, and how a result is evaluated. My experience spans banking technology and logistics, alongside software engineering at Polytechnique Montréal. This portfolio brings those threads together through projects you can explore. Each case study makes room for the decisions, constraints, and limitations behind the work, as well as the next steps needed to make it stronger.

A little more code on GitHub
LET’S CONNECT

Have somethingin mind?

For software development, applied AI, or a conversation about the work — my inbox is open.