Computer Science @ York University · Full-Stack & AI/ML Engineer · Toronto, ON
I build scalable systems - from AI automation platforms to real-time data pipelines. Passionate about turning complex problems into clean, impactful software.
Full-stack AI orchestration platform coordinating intelligent agents for scalable task automation.
- Architected platform using Next.js + FastAPI, enabling orchestration across Planner, Memory, and Summarizer agents
- Improved task execution efficiency by 35% via RESTful agent coordination APIs
- Deployed on AWS ECS with Docker + CI/CD pipelines — reduced deployment time by 50%
- Implemented RAG with vector database for enhanced contextual memory and response accuracy
Next.js FastAPI LangGraph Docker AWS ECS RAG Python
End-to-end ML pipeline for real-time stock analysis with an interactive Streamlit dashboard.
- Engineered data pipeline improving processing efficiency by 40%
- Reduced manual data collection effort by 90% via Yahoo Finance API automation
- Built interactive real-time visualization dashboard for faster, data-driven trading decisions
Python Machine Learning Streamlit Yahoo Finance API
🎬 RateFlix
Full-stack desktop app for movie discovery with personalized watchlists and real-time TMDB content sync.
- Designed and optimized MySQL relational schema, cutting data retrieval latency by 30%
- Built full authentication system with personalized watchlists and review management
- Integrated TMDB REST API for dynamic, real-time content updates and enhanced UX
Java Swing MySQL TMDB API
| Category | Technologies |
|---|---|
| Languages | Python, Java, JavaScript, SQL, R, HTML/CSS |
| Frameworks | React, Next.js, FastAPI, Flask, Node.js, Streamlit |
| Cloud & Tools | AWS (ECS), Docker, Git, CI/CD, Google Cloud, VS Code |
| Databases | MySQL, Vector Databases |
| Concepts | REST APIs, Microservices, RAG, Agile, Full-Stack Dev, ML Inference |
| Metric | Result |
|---|---|
| Data pipeline efficiency | ↑ 40% |
| Manual data collection eliminated | ↓ 90% |
| Deployment time reduction | ↓ 50% |
| Agent task execution efficiency | ↑ 35% |
| DB retrieval latency reduction | ↓ 30% |
- Civic Tech Toronto — Contributing to open-source civic applications; improving code quality via pull requests and Agile workflows
- AI Club @ York University — Exploring ML concepts: neural networks, model evaluation, real-world AI system design
- CS Hub @ York — Full-stack dev & cloud workshops, hackathons, peer collaboration
"Build things that matter. Measure the impact. Iterate."