/ai · APPLIED LLM SYSTEMS

I orchestrate LLMs into products that ship — and don't go bankrupt.

Multi-provider fallback chains, RAG over 40+ languages, multi-agent systems, and prompt caching that cut generation cost by ~95%.

3 providers

Anthropic → Gemini → OpenAI fallback chain

~95%

cost cut via 24h prompt caching

40+

languages in production RAG

3 agents

orchestrated with code-enforced rules

AI PROJECTS

LLM systems I've shipped

FLAGSHIP

AI sales-intelligence platform: multi-owner RBAC, idempotent assignment service, 8-phase zero-downtime migration, multi-provider LLM coaching.

Python · Flask · MongoDB · LLMs

AI · BACKEND

AI career platform across a 5-service architecture. GPT-4o + Gemini fallback, conversational data extraction, real-time Socket.IO + SSE.

Node · TS · React · MongoDB

AI · BACKEND

Multi-tenant AI education platform: institutional RBAC hierarchy, per-student token quotas, cost-analytics, scoped agent API keys.

TS · React · Node · Azure

AI · RAG

Multilingual RAG assistant over 40+ languages on a LangChain pipeline with Gemini + OpenAI fallback and MongoDB backup infra.

TS · Node · Azure Blob

AI · AGENTS

Multi-agent trip planner: Gemini function-calling routes destination, itinerary & budget agents with code-enforced behavioral rules.

TS · Express · React · Docker