I build quick, smart, and scalable AI solutions for businesses looking to level up their operations — from sharpening fundamentals in notebooks, to shipping LLM-powered applications, to end-to-end systems in production.
- 🧪 Foundational ML & Statistical Modeling — notebook-based work that keeps the core sharp
- 🤖 Applied LLM Engineering — RAG systems, agents, document AI
- 🚀 End-to-End AI Systems — production-grade, deployed, monitored
YouTube Compliance Workflow — an LLMOps pipeline on Azure using a multi-agent architecture to automate content compliance review. Azure · LangChain · multi-agent orchestration · LLMOps tooling
Repo goes public when it's ready.
Developing multi-agent systems on the Azure ecosystem.
Clean, well-documented experiments grounded in classical ML and statistical theory.
- Predicting-Heart-Disease — Comparative study of KNN, Random Forest, XGBoost, and Neural Networks on clinical data. Jupyter · scikit-learn · XGBoost
- Monte-Carlo-Simulation — Decision trees vs. random forests across 8 scenarios. R
- Maintenance-Predictive — Random Forest for predictive maintenance scheduling. R
Building with modern language model stacks.
- PharmaOCR — LLM-powered OCR engine that reads and understands pharmaceutical documents. Python · LangChain · OpenAI
- brevio-ai — Personalized news digests via LLM summarization and automated email delivery. Python · OpenAI
- StaffBot (Hackathon) — Candidate-job matching with semantic analysis and multi-criteria scoring. Python · LangChain · ChromaDB
In progress — see Currently Building above.
Languages & Data
ML & AI
Cloud & DevOps
Automation & Low-Code
HEC Montréal — M.Sc. in Machine Learning Polytechnique Montréal — B.Eng. in Industrial Engineering & Applied Mathematics
Open to opportunities.