Data & AI-Application Engineer
Production AI Systems, Built to Ship
LangGraph agents · RAG · Data pipelines
During a Master of Data Analytics in Canada (GPA 4.13/4.3), I designed, built, and tested projects end to end: a ~20-node LangGraph job-search agent, an advanced hybrid-retrieval RAG system for safety-critical aviation docs (LearnArken), and a geospatial climate analysis of 275,156 trees. Authorized to work full-time in Canada now — no employer sponsorship required, available immediately.
Recent Hands-On Work
From data to model to shipped — end to end.
LLM Agents & Orchestration
LangGraph evaluation pipeline
A ~20-node LangGraph StateGraph that takes a job description and produces a fit score plus a tailored resume and cover letter; LLM calls run across the Claude and OpenAI APIs with structured outputs and graceful fallback, covered by 460+ pytest tests.
RAG & Retrieval
Hybrid retrieval, reranking, and fail-closed grounding
In LearnArken, a RAG system for safety-critical aviation docs: hybrid BM25 + dense retrieval fused with RRF, a cross-encoder reranker, and a Neo4j graph for multi-hop questions — with three fail-closed gates and verbatim-quote citations so it refuses rather than fabricates.
Product & Business Sense
Engineering shaped by real product ownership
Years leading product and technology — ride-hailing SaaS fleet tools, consumer apps at 10k+ DAU — mean I build with the business model and the end customer in view. I talk to users, turn needs into specs, and communicate across functions, rather than ship code in isolation from the people it serves.