A DevOps Specialist turned AI builder — designing agentic pipelines, RAG systems, and MCP servers on top of solid data engineering and CI/CD foundations.
I turn brittle, manual workflows into self-running systems. At CIBC I was promoted from Junior to DevOps Specialist by automating deployments and hardening CI/CD across SIT, UAT and production — [add your headline metric here: e.g. "cutting release time by X%"].
Now I apply that same reliability mindset to AI: agentic pipelines, RAG systems, and MCP servers, backed by real data engineering on Databricks and Delta Lake. The goal isn't a demo — it's an AI system a team can actually depend on.
I work spec-first: define the behavior, write the test, then build. It's how I keep AI systems dependable instead of magical-until-they-break.
Live projects are on the way. Each will land here with the problem it solved, how it was built, and a link to the code.
Result: [the outcome — e.g. "automated a 3-hour manual task down to 4 minutes"]
Problem: [what was broken] · My role: [what you built]
Result: [the outcome — e.g. "answers grounded in 500+ private docs"]
Problem: [what was broken] · My role: [what you built]
Result: [the outcome — e.g. "cut pipeline runtime by X%"]
Problem: [what was broken] · My role: [what you built]