About

I'm a machine learning developer building production ML systems and agentic AI applications. I focus on recommendation systems, retrieval-augmented generation, and multi-agent architectures that combine LLMs with specialized tools and real-time data retrieval. My business degree (HEC Montréal, bilingual IT program) helps me bridge technical implementation and business requirements, ensuring ML solutions deliver measurable value.

What I build

• Agentic AI systems: LLM-powered agents with tool orchestration (LangGraph), RAG pipelines with vector search (FAISS), and multi-turn conversation management across specialized capabilities.
• Production ML systems: Real-time recommendation engines with collaborative filtering (ALS), attention-pooled embeddings, hybrid similarity search, and automated MLOps pipelines for model retraining and deployment.
• Data infrastructure for ML: Event-driven pipelines (Kafka, Spark), semantic embedding generation, SQL schemas optimized for ML workloads, and artifact versioning with safe rollbacks.

How I solve problems

• Frame the outcome: Identify the user action or business goal; pick metrics that actually reflect it.
• Ship a baseline: Create a simple, verifiable version early (straightforward SQL/API or heuristic) to de-risk the path.
• Iterate with evidence: Add complexity only if it demonstrably improves results, latency, or reliability.
• Design for change: Stable interfaces between components (ingest, store, serve) so each can evolve independently.
• Keep ops simple: Idempotent jobs, explicit rollbacks, structured logs, and basic dashboards to answer "is it healthy?"

Engineering practices I care about

• Readable code: Small modules, consistent naming, guardrails (assertions/invariants), and good boundaries.
• Reproducible data: Deterministic exports, documented transformations, and leakage-aware evaluation.
• Performance budgets: Aim for predictable tail latency; cache or precompute when it simplifies serving.
• Documentation: Short design notes and runbooks that explain intent, interfaces, and failure modes.

Selected project

Book Recommendation System (production): End-to-end ML platform with a real-time recommendation engine and conversational AI interface. The recommendation API serves personalized suggestions with sub-50ms latency using dual-factor architecture (ALS collaborative filtering + attention-pooled subject embeddings). Built a multi-agent chatbot on top using LangGraph that orchestrates 8+ specialized tools to provide natural language access to the recommendation system, semantic search, and external knowledge sources.

• Recommendation engine: ALS collaborative filtering for warm users, attention-pooled subject embeddings for cold-start, hybrid similarity search, automated MLOps pipeline with scheduled retraining and hot-reload deployments achieving sub-50ms inference.
• Conversational agent: LangGraph-based multi-agent system with router/conductor/specialized agents, RAG with FAISS vector search for semantic retrieval, tool orchestration (recommendation APIs, catalog search, web search), and multi-turn conversation memory.
• Data infrastructure: Event-driven enrichment pipeline (Kafka, Spark) for semantic metadata generation, normalized SQL schema, vector index management, and comprehensive testing suite (55+ integration tests).

Before programming

From age seven to sixteen I practiced karate, earning a black belt at fifteen. A few months later, I broke a cement block with my bare hands, something I would have thought impossible when I started. Karate taught me discipline and perseverance, and proved that limits could be surpassed with consistent effort over time. It gave me a framework for mastering any skill.

Around the same period, I ran a student lawn care company from ages 15 to 18. I found clients, managed schedules, and employed friends. It was my first time building something entirely on my own, with no one above me to rely on. That experience taught me independence, accountability, and what it means to be fully responsible for a project from start to finish.

Later, I taught myself music production from scratch on my computer, having never played an instrument. It was the first time I learned a completely new skill without guidance, which gave me a lasting meta-skill: learning how to learn. Although I eventually shifted focus to programming and machine learning, I still create music occasionally.

Business background

While I was building side projects like the book recommender and experimenting with music, I also completed a bilingual bachelor's degree in business at HEC Montréal, with a specialization in information technology. That gave me the business mindset most engineers lack, thinking in terms of value, trade-offs, and strategy, while my projects and technical learning gave me the technical depth most business grads don't have, especially in machine learning. This combination means I approach problems with both the technical tools to build and the business context to prioritize.

Learning & certifications

AWS Certifications

• AWS Certified Machine Learning - Specialty (MLS-C01) | Score: 890/1000 | Jan 2026
• AWS Certified Generative AI - Professional (AIP-C01) | Early Adopter (First 5000) | Jan 2026

Courses & Professional Development

• FreeCodeCamp: Back End Development & APIs, Quality Assurance, Information Security, Scientific Computing with Python, Data Analysis with Python, Machine Learning with Python, Foundational C#.
• MIT Missing Semester, MIT Intro to Deep Learning
• fast.ai Practical Deep Learning for Coders (Parts 1 & 2)
• DeepLearning.AI: AI for Everyone, Generative AI for Everyone, Agentic AI
• Microsoft Learn: Azure cloud and C#/.NET paths

University Coursework

• SQL, Python for data analysis, Cybersecurity fundamentals

Self-study & References

• Web fundamentals (HTML, CSS, JavaScript, PHP) via W3Schools tutorials and MDN Web Docs (reference documentation; not a certification)

Current Focus

• Systems design for low-latency services, robust data contracts, and practical ML for ranking/prediction

Tech I use

How I work with others

• Clear communication: concise design notes, explicit trade‑offs, and honest status updates; bilingual (FR/EN).
• Ownership: I’m comfortable carrying a feature from design to rollout, and writing the docs/runbooks that stick around.
• Mentorship-by-default: leave the codebase easier to understand than I found it: naming, comments, examples, and tests.

What I'm looking for

I'm looking for ML roles where I can work on production systems around LLMs, agentic AI, and recommendation engines. I want to contribute across the ML lifecycle: data pipelines, model training, deployment, and iteration based on real-world feedback. I'm particularly interested in teams building RAG systems, tool-calling architectures, or personalization at scale. My business background helps me connect technical decisions to product outcomes, and I'm looking for a team where I can grow these skills while learning from experienced practitioners.