Multimodal Macro-Nutrient Pipeline & GenAI Dietary Optimization Engine

Architected a cross-modal meal-logging pipeline and a RAG-based dietary optimization engine for a diabetes-management product.

Architected a cross-modal pipeline (ASR + NLP + Vision, slot-filling, Gemini + pgVector ANN) over a 10,000+ recipe / 30,000+ alias database for daily meal logging, resolving dish matches in ~2s (DB-backed) to 3–5s (LLM fallback) at ~90% accuracy. Powered a RAG meal-plan engine with behavioral signals and condition-specific diabetic constraints.