Bridging infrastructure depth with client-facing solution delivery, RAG systems, multi-agent AI, and applied LLM engineering.
👥
Client Discovery & Solution Delivery
Running FDE Academy's PizzaFlow (SliceMatic) engagement — translating a real client's ambiguous requirements into a structured technical spec, then shipping a live Vercel + Supabase + LangChain AI ordering platform. From stakeholder discovery to production deployment.
Use-Case DiscoveryRequirements SpecFDE AcademySliceMatic
🧠
LLM, RAG & Multi-Agent Systems
Building RAG pipelines, multi-agent workflows, MCP integrations, and LLM-powered applications using LangChain, OpenRouter, and Google AI Studio. Experienced in prompt engineering, multimodal models, GenAI, and AIOps — using Claude, ChatGPT, and Gemini daily.
RAGLLM SystemsMulti-AgentMCPGenAIAIOps
⚓
MLOps & Kubernetes for AI Workloads
Deep expertise in Kubernetes HA, TLS, Helm chart authoring, GPU node management (NVIDIA/CRI-O), and MLOps with Prefect v3 on EKS. Managing production AI inference clusters for enterprise healthcare with AIOps-grade observability.
MLOpsKubernetes HAHelm ChartsGPU NodesPrefect v3
△
Full-Stack AI: Vercel + Supabase + n8n
Shipped production AI apps using Vercel for frontend, Supabase for PostgreSQL + Auth backend, and n8n for intelligent workflow automation. Built SliceMatic and Task Manager — complete FDE delivery stack from prompt to live product.
VercelSupabasen8nLangChainOpenRouterReplit