Background
I'm an AI Systems Engineer with 5+ years of experience designing and deploying production-grade intelligent systems. My work sits at the intersection of large language models, agentic workflows, and scalable backend architecture — building the full stack from research prototype to production deployment.
Currently, I'm a Machine Learning Developer at CanApply (NovaVidya Inc.) in Montreal, where I've built everything from multi-agent AI orchestration platforms and distributed conversational systems to large-scale academic data crawling infrastructure.
I'm also co-building Trellion, an AI-native hiring intelligence platform that replaces manual resume screening with automated evaluation pipelines.
What I Build
My core strength is turning complex AI research and tooling into production systems that actually work — reliably, at scale, under real operational constraints.
That means:
- LLM systems and agentic workflows — multi-agent orchestration, RAG/CAG pipelines, structured output validation, hybrid retrieval architectures
- Scalable microservices — FastAPI-based REST APIs, Kafka message pipelines, Dockerized deployments, Redis caching, CI/CD
- AI data products — web crawlers, document extraction engines, semantic search systems, recommendation pipelines
- Machine learning — from classical models (financial time series, NLP) to deep learning (GNNs, vision transformers, reinforcement learning)
Research
I've contributed to academic research in robotics localization (RoboCup Symposium 2025) and environmental data science (Nature Portfolio, 2026). My research interests span autonomous systems, ML for scientific data, and applied NLP.
Background & Education
I hold an Honours BSc in Computer Science from Lakehead University (Thunder Bay, Canada). Before focusing on AI, I spent several years as a quantitative software engineer building financial data pipelines, algorithmic trading systems, and analytics platforms for equity and crypto markets.
Outside Work
I care about building things that are both technically sound and practically useful. I'm drawn to problems where the gap between "research works" and "production works" is large — and closing that gap is the interesting part.
If you want to talk about a project, a role, or anything in the AI/systems space, reach out.